© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237145
    Prev
    Next
    INDEX
    Explanations

    Whitney Houston

    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_32_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
     조직
    0.41
     투
    0.40
    idelberg
    0.39
    gment
    0.38
    izoen
    0.38
     изобра
    0.38
    തം
    0.37
     penj
    0.37
     ción
    0.37
     செய்து
    0.36
    POSITIVE LOGITS
    Whitespace
    0.41
    &$
    0.38
    Camp
    0.38
    SMS
    0.37
    خد
    0.36
    एँ
    0.36
     লী
    0.35
    ulis
    0.34
     Zil
    0.34
    attere
    0.34
    Activations Density 0.000%

    No Known Activations