© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204932
    Prev
    Next
    INDEX
    Explanations

    exam abbreviations and subsequent terms

    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_37_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
     dif
    0.42
    DID
    0.40
    Manip
    0.38
     ^^
    0.37
     accred
    0.37
     Manip
    0.36
    בום
    0.36
     Offic
    0.36
    ffi
    0.36
    did
    0.35
    POSITIVE LOGITS
    entr
    0.47
    വിധ
    0.37
     Entrada
    0.36
     announcing
    0.35
    ライブ
    0.35
     영
    0.34
     вопро
    0.34
     जनते
    0.34
     entrance
    0.33
     notable
    0.33
    Activations Density 0.000%

    No Known Activations