© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14999
    Prev
    Next
    INDEX
    Explanations

    initialed names

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    np_max-act · gemini-2.0-flash

    say "." Method used: 2 — because tokens after the max activators are predominantly "."

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GEBURTSDATUM
    -0.89
     whoſe
    -0.79
    原始内容存档于
    -0.77
    #+#
    -0.77
     raiſ
    -0.75
     ſche
    -0.72
     houſe
    -0.70
     InputDecoration
    -0.70
    WebServlet
    -0.69
     theſe
    -0.68
    POSITIVE LOGITS
     McC
    0.60
     Mc
    0.60
    ECONDS
    0.54
     $
    0.54
    ">)</
    0.49
     von
    0.49
     Roskov
    0.48
    cademic
    0.47
    mately
    0.47
     Frucht
    0.47
    Activations Density 0.738%

    No Known Activations