© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90351
    Prev
    Next
    INDEX
    Explanations

    urban appearance, background, property, governance

    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
    =\
    0.69
    ாத
    0.68
    ྥ
    0.67
    ാവ
    0.65
    ਆਂ
    0.64
    א
    0.64
    ق
    0.63
    ن
    0.63
    یت
    0.62
    ாது
    0.61
    POSITIVE LOGITS
    ↵
    0.66
    AS
    0.64
    u
    0.62
    会在
    0.61
    여
    0.59
    Urban
    0.58
    to
    0.57
    urit
    0.56
    urian
    0.56
    urban
    0.56
    Activations Density 0.046%

    No Known Activations