© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86417
    Prev
    Next
    INDEX
    Explanations

    kangaroos and aquaponics

    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_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
    s
    0.78
    ཋ
    0.70
     CLIENTI
    0.67
    이란
    0.66
    Puedes
    0.65
    denoted
    0.64
    r
    0.63
     consta
    0.63
    deriv
    0.63
    también
    0.62
    POSITIVE LOGITS
     as
    0.96
    </h3>
    0.86
    aks
    0.62
    ام
    0.61
    eks
    0.60
    ies
    0.60
    ב
    0.60
     at
    0.59
    ography
    0.59
    "?>
    0.59
    Activations Density 0.000%

    No Known Activations