© 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. 8253
    Prev
    Next
    INDEX
    Explanations

    past events

    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
    ו
    1.13
    н
    1.11
    ে
    1.08
    lug
    1.08
    菌
    1.03
    at
    1.02
     superscript
    1.01
    েই
    0.96
     cohomology
    0.95
    ection
    0.95
    POSITIVE LOGITS
     autrefois
    1.19
    wolves
    0.99
    𝐶
    0.99
    ہ
    0.93
    withTrashed
    0.93
    য়ের
    0.89
    нить
    0.87
    Ти
    0.83
    более
    0.82
    previously
    0.82
    Activations Density 0.015%

    No Known Activations