© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7849
    Prev
    Next
    INDEX
    Explanations

    last minute

    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
    l
    2.27
    ع
    2.21
    ল
    2.08
    ন
    2.06
    avirus
    1.97
    లో
    1.97
    getto
    1.97
     constitutive
    1.97
    ী
    1.95
    로
    1.92
    POSITIVE LOGITS
     pores
    2.26
     सिरे
    2.11
     vendar
    2.04
     sít
    2.04
    ো
    2.04
    다
    2.02
     avis
    2.02
    ശാ
    1.92
    ות
    1.91
     पर्यंत
    1.91
    Activations Density 0.042%

    No Known Activations