© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5398
    Prev
    Next
    INDEX
    Explanations

    shrink

    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_3_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
    ytale
    3.05
    
    2.68
     glimpse
    2.43
    一来
    2.36
    ње
    2.29
    rtype
    2.29
     मैथ
    2.22
    eighth
    2.19
    িত্যক্ত
    2.08
    靂
    2.07
    POSITIVE LOGITS
     wonders
    2.68
    sofar
    2.65
    𝒅
    2.54
     Showtime
    2.36
     cruciate
    2.34
    Typography
    2.31
     footprint
    2.27
    진다
    2.24
    𝚍
    2.24
    忡
    2.22
    Activations Density 0.045%

    No Known Activations