© 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. 8448
    Prev
    Next
    INDEX
    Explanations

    replays, files, played

    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
    การ
    2.39
    ে
    2.37
     averted
    2.35
     propensity
    2.23
    ب
    2.20
    การณ์
    2.06
     importantly
    2.02
    杮
    2.01
     ascertained
    1.96
    ⟶
    1.93
    POSITIVE LOGITS
    ى
    2.26
    н
    2.21
    ान
    2.19
    te
    2.15
     sauvegard
    2.12
    虑
    2.04
    ផ្សេង
    2.04
    べき
    2.04
    вни
    2.04
     nemmeno
    2.01
    Activations Density 0.067%

    No Known Activations