© 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. 7875
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
    ging
    0.86
    y
    0.83
    tt
    0.81
     wob
    0.79
    isNull
    0.78
    g
    0.77
    yak
    0.76
     hora
    0.75
    орк
    0.75
    ঙ্ক
    0.73
    POSITIVE LOGITS
    &-
    0.91
     confining
    0.90
    chyma
    0.90
    ో
    0.89
    ductory
    0.88
    ה
    0.86
     masalah
    0.85
    শীল
    0.84
     dolayı
    0.83
     gsub
    0.82
    Activations Density 0.005%

    No Known Activations