© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24068
    Prev
    Next
    INDEX
    Explanations

    Amsterdam and places

    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_56_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
     tarot
    0.41
    []');
    0.40
    plaf
    0.40
    эг
    0.38
    tsConfig
    0.37
    ﹊
    0.37
     стреми
    0.36
     कार्ड
    0.36
     hopes
    0.35
     grafo
    0.35
    POSITIVE LOGITS
    Illegal
    0.39
    hind
    0.38
    TRO
    0.37
    alis
    0.37
    hoc
    0.36
     बोले
    0.36
    ाई
    0.35
    $)
    0.35
    НЯ
    0.35
    hing
    0.35
    Activations Density 0.001%

    No Known Activations