© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3859
    Prev
    Next
    INDEX
    Explanations

    expressions of dislike, negativity, or disagreement.

    oai_token-act-pair · gemini-2.0-flash

    Expressing opinions/feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     much
    -1.37
     many
    -1.35
    much
    -1.21
     muchas
    -1.20
    many
    -1.19
    Much
    -1.19
    Many
    -1.16
     Many
    -1.14
     Much
    -1.11
     muchos
    -1.10
    POSITIVE LOGITS
     Quite
    0.59
     quite
    0.56
    quite
    0.52
    Quite
    0.52
    riwal
    0.47
    Personendaten
    0.45
     so
    0.45
    новить
    0.44
    bos
    0.43
    AddAttribute
    0.43
    Activations Density 2.704%

    No Known Activations