© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 2902
    Prev
    Next
    INDEX
    Explanations

    Edith Finch

    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
    an
    1.76
    swering
    1.67
    cd
    1.65
    ان
    1.63
    col
    1.61
    ל
    1.61
    nement
    1.55
    yt
    1.55
    wwww
    1.54
    it
    1.53
    POSITIVE LOGITS
    ecycle
    1.59
    儡
    1.47
    ulents
    1.44
    𝙤
    1.41
    楇
    1.40
     averaging
    1.40
    માન
    1.38
    𝙮
    1.38
    ែ
    1.37
     mezzanine
    1.36
    Activations Density 0.001%

    No Known Activations