© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3480
    Prev
    Next
    INDEX
    Explanations

    position:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gebra
    1.17
    স
    1.11
     usu
    1.10
    どうか
    1.05
     thách
    1.05
     uz
    1.05
    ıma
    1.02
    éros
    1.02
     chiqar
    1.01
     esper
    1.01
    POSITIVE LOGITS
    ANCE
    1.31
    centroids
    1.23
    ,\,\
    1.22
     médian
    1.20
    LAY
    1.20
    ං
    1.20
     ents
    1.19
     одно
    1.19
    বিষ্য
    1.18
     accusing
    1.17
    Activations Density 0.022%

    No Known Activations