© 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-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88723
    Prev
    Next
    INDEX
    Explanations

    potential damage or loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     Trot
    0.38
    DY
    0.38
     DY
    0.37
     memory
    0.37
    ulario
    0.36
    memory
    0.36
     retained
    0.36
    ੱ
    0.35
    HT
    0.35
     circulated
    0.34
    POSITIVE LOGITS
     Norwood
    0.48
    hamilan
    0.40
    Capabilities
    0.39
    🖉
    0.39
    மிக
    0.38
    澤
    0.38
    WindowClass
    0.38
     яс
    0.38
     Hawker
    0.38
     способность
    0.38
    Activations Density 0.018%

    No Known Activations