© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78877
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ী
    0.70
     CAUSED
    0.66
     ASPECTS
    0.65
    ျ
    0.64
    شی
    0.64
     HAVE
    0.64
     WHICH
    0.64
    ಷ್ಟು
    0.63
    سی
    0.62
     EXAMPLE
    0.62
    POSITIVE LOGITS
    2
    0.97
     is
    0.76
    erv
    0.71
    ja
    0.70
    čin
    0.69
    ка
    0.69
    fläche
    0.66
    flächen
    0.64
    不僅
    0.64
    _
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.