© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59932
    Prev
    Next
    INDEX
    Explanations

    say "la"

    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_59_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
    lok
    0.46
    ethe
    0.45
    the
    0.42
    De
    0.42
    lung
    0.41
     De
    0.41
    lle
    0.39
    }$;
    0.39
    de
    0.39
    thema
    0.39
    POSITIVE LOGITS
     La
    0.68
    La
    0.66
     Lá
    0.63
     Le
    0.59
     Lo
    0.56
     Laid
    0.54
    Le
    0.53
    Lambda
    0.52
    Lo
    0.51
     Lay
    0.51
    Activations Density 0.003%

    No Known Activations