© 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. 45996
    Prev
    Next
    INDEX
    Explanations

    South Park and side

    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
    X
    0.72
     The
    0.71
     and
    0.68
    1
    0.68
     in
    0.65
     Exel
    0.63
     was
    0.63
     And
    0.61
     en
    0.60
     increíble
    0.60
    POSITIVE LOGITS
    ა
    0.82
    ون
    0.78
    ونها
    0.70
    is
    0.64
    ርግ
    0.63
    Masukkan
    0.63
    ુ
    0.61
    اس
    0.59
     cheek
    0.58
     بیشتری
    0.58
    Activations Density 0.000%

    No Known Activations