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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6353
    Prev
    Next
    INDEX
    Explanations

    list items or abbreviations

    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
    ಾಪ
    1.19
    gie
    1.11
    𝗻
    1.11
     Epistle
    1.10
    atts
    1.09
     toned
    1.08
     qq
    1.07
    ேயே
    1.06
     zusätzlichen
    1.06
     subclasses
    1.05
    POSITIVE LOGITS
    и
    1.38
    ১
    1.35
    ни
    1.18
    is
    1.12
    ش
    1.07
    ার
    1.07
    ය
    1.06
    우리
    1.04
    ين
    1.03
    ה
    1.02
    Activations Density 0.001%

    No Known Activations