© 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. 10414
    Prev
    Next
    INDEX
    Explanations

    articles about related items coming in specific low amounts

    oai_token-act-pair · gemini-2.0-flash

    two/couple

    np_max-act · gemini-2.0-flash

    two

    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
     useful
    -0.51
     Blau
    -0.50
    maha
    -0.50
     съм
    -0.49
    ]")]
    -0.48
     rigue
    -0.47
     Hoffmann
    -0.46
    malo
    -0.45
     库存
    -0.45
    便利な
    -0.45
    POSITIVE LOGITS
    __":
    0.81
    tagext
    0.80
    __":
    0.77
    __':
    0.76
    UnusedPrivate
    0.74
     HasFactory
    0.71
    yntaxException
    0.71
    Personendaten
    0.69
     CURIAM
    0.68
    WireFormatLite
    0.68
    Activations Density 1.352%

    No Known Activations