© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 103367
    Prev
    Next
    INDEX
    Explanations

    say fossil

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     Pearls
    0.44
     fertile
    0.43
     څر
    0.43
     normalen
    0.42
    ROUTE
    0.40
     novoProduto
    0.40
     NORMAL
    0.40
    <unused357>
    0.40
     fruitful
    0.39
     tradicion
    0.38
    POSITIVE LOGITS
    geti
    0.38
    ogen
    0.37
    eled
    0.37
    mas
    0.36
    amsu
    0.36
    越高
    0.36
    âm
    0.36
    hene
    0.36
     emuls
    0.36
     Maserati
    0.36
    Activations Density 0.003%

    No Known Activations