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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9755
    Prev
    Next
    INDEX
    Explanations

    punctuation ,

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    ୍ର
    0.79
    
    0.75
    =",
    0.74
    pubescens
    0.74
     ねえ
    0.69
    yatiti
    0.68
     "),
    0.68
    midrule
    0.68
    itamento
    0.67
     Ін
    0.67
    POSITIVE LOGITS
    ,
    2.58
    ،
    2.37
    、
    2.13
    ，
    2.00
    ፣
    1.91
     ،
    1.74
    ,\
    1.70
     ,
    1.61
    、「
    1.56
    ,<
    1.55
    Activations Density 0.336%

    No Known Activations