© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14103
    Prev
    Next
    INDEX
    Explanations

    YouTube URLs

    oai_token-act-pair · gemini-2.0-flash

    URLs and web links

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    parsedMessage
    -0.96
     متعلقه
    -0.87
    __':
    -0.82
    tvguidetime
    -0.81
    ArgsConstructor
    -0.80
    printStackTrace
    -0.78
    onViewCreated
    -0.78
     MonoBehaviour
    -0.77
    gorov
    -0.77
    ruptedException
    -0.74
    POSITIVE LOGITS
    ps
    0.49
    op
    0.46
    a
    0.46
    id
    0.44
    t
    0.42
    ci
    0.42
    p
    0.42
    tss
    0.41
    pur
    0.41
    eff
    0.41
    Activations Density 1.169%

    No Known Activations