© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204617
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    出
    0.48
    л
    0.47
     détail
    0.46
    ল
    0.46
     ఇవ్వ
    0.45
     Vielen
    0.45
    oi
    0.45
    im
    0.45
    па
    0.45
     самом
    0.44
    POSITIVE LOGITS
     aeronaut
    0.45
     playerScore
    0.45
    -$\
    0.45
     cairan
    0.45
    hna
    0.44
    aroos
    0.42
     salesmen
    0.42
    habilitation
    0.42
    umlah
    0.42
    resu
    0.42
    Activations Density 0.000%

    No Known Activations