© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205463
    Prev
    Next
    INDEX
    Explanations

    Melaleuca, Serviceberry, Virginia Creeper

    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_6_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
     पुअनि
    0.95
     службы
    0.90
    ал
    0.85
     መጠቀም
    0.84
     pertenece
    0.83
    ட
    0.82
     conex
    0.82
    ルの
    0.81
     contrived
    0.80
    સિંહ
    0.79
    POSITIVE LOGITS
     It
    1.08
     If
    0.97
     to
    0.97
     (
    0.96
     En
    0.96
     an
    0.95
     Nä
    0.92
     In
    0.90
     is
    0.89
     An
    0.89
    Activations Density 0.000%

    No Known Activations