© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14127
    Prev
    Next
    INDEX
    Explanations

    the letter "E"

    oai_token-act-pair · gemini-2.0-flash

    the letter 'E'

    np_token-act-pair-logits · gpt-4o-mini

    E

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    轭
    -0.61
    ReusableCell
    -0.57
    qvarna
    -0.52
    ografia
    -0.50
    apist
    -0.50
    __*/
    -0.48
    toISOString
    -0.48
    gdx
    -0.48
    prepareStatement
    -0.47
    Portale
    -0.47
    POSITIVE LOGITS
    ]--;
    0.56
    SerializedName
    0.55
    LLocation
    0.52
    ódź
    0.51
     Così
    0.50
    +#+#
    0.50
    TokenName
    0.48
    WebElementEntity
    0.48
    __);
    0.47
    olastic
    0.47
    Activations Density 0.423%

    No Known Activations