© 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. 6460
    Prev
    Next
    INDEX
    Explanations

    masturbating

    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
    A
    2.69
    𝘵
    2.69
    biotic
    2.60
     verbatim
    2.55
    岖
    2.47
     aad
    2.43
    ɦ
    2.38
    Certainly
    2.37
    𝗵
    2.36
    ular
    2.34
    POSITIVE LOGITS
    на
    3.10
    ${
    2.89
    ни
    2.74
     gravi
    2.70
    ர்
    2.60
    দারি
    2.54
    ००
    2.36
    ν
    2.35
     bbox
    2.30
    naire
    2.29
    Activations Density 0.010%

    No Known Activations