© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14830
    Prev
    Next
    INDEX
    Explanations

    names of famous people

    oai_token-act-pair · gemini-2.0-flash

    celebrities

    np_max-act · gemini-2.0-flash

    celebrity surnames Method used: 1 — because the max activating tokens are celebrity last names — celebrity surnames

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )))));
    -0.63
    __*/
    -0.59
    帖最后由
    -0.58
    '}),
    -0.55
    XmlType
    -0.55
    '],
    -0.53
    ']>
    -0.52
    \}=
    -0.51
     ""],
    -0.50
    "":
    -0.50
    POSITIVE LOGITS
     BoxDecoration
    0.45
    printStackTrace
    0.43
    Географија
    0.40
     Monfieur
    0.40
     Shakspeare
    0.40
    DispatchToProps
    0.40
     neceff
    0.39
    lorette
    0.39
     Efq
    0.38
     Hift
    0.38
    Activations Density 0.131%

    No Known Activations