© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36898
    Prev
    Next
    INDEX
    Explanations

    Baldur's Gate, Shell, banana, cre[ek]

    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
    r
    1.14
    n
    0.93
    ل
    0.83
    nThe
    0.81
    l
    0.80
    P
    0.77
    H
    0.77
    し
    0.76
    ন
    0.75
    ن
    0.74
    POSITIVE LOGITS
    ี
    0.78
     congenital
    0.71
     transcendent
    0.69
    ння
    0.68
     fibrin
    0.64
    ς
    0.64
    ︎
    0.64
    \
    0.62
    ;
    0.61
     attaché
    0.60
    Activations Density 0.004%

    No Known Activations