© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3500
    Prev
    Next
    INDEX
    Explanations

    roulette, through mountains, Everest

    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
    l
    0.54
     Questa
    0.50
     elucidated
    0.48
    tól
    0.47
     SFR
    0.47
    atisf
    0.47
    ड
    0.47
    ukawa
    0.46
    in
    0.46
    listed
    0.46
    POSITIVE LOGITS
     состоянии
    0.41
     во
    0.40
    кро
    0.39
     thes
    0.39
     disposit
    0.38
    }=\
    0.37
    }<\
    0.37
    }.$
    0.37
     хозяй
    0.36
     graze
    0.36
    Activations Density 0.003%

    No Known Activations