© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11135
    Prev
    Next
    INDEX
    Explanations

    statistics and percentages

    oai_token-act-pair · gemini-2.0-flash

    percentages and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ]")]
    -0.74
     للمعارف
    -0.61
    Hentet
    -0.58
     utafitiHapana
    -0.57
    ագրություններ
    -0.56
     poveznice
    -0.55
     probes
    -0.54
     honom
    -0.54
     transfieras
    -0.52
    zzini
    -0.50
    POSITIVE LOGITS
    RTEX
    0.53
    propTypes
    0.53
    spender
    0.53
     Safety
    0.51
    Fourth
    0.50
    DBNull
    0.50
     unknownFields
    0.48
     Generales
    0.48
    noopener
    0.47
    safety
    0.47
    Activations Density 1.827%

    No Known Activations