© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3117
    Prev
    Next
    INDEX
    Explanations

    things followed by punctuation or clauses

    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
    يات
    1.67
    ta
    1.59
    rg
    1.59
     रुख
    1.51
    rf
    1.50
     else
    1.48
    )$.
    1.44
    or
    1.43
    yrs
    1.41
    rx
    1.40
    POSITIVE LOGITS
    然後
    1.82
    ১
    1.64
    αν
    1.50
    émie
    1.48
    н
    1.47
    Дан
    1.47
    Есть
    1.46
    Die
    1.44
    ال
    1.43
    ﾞ
    1.43
    Activations Density 0.026%

    No Known Activations