© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206677
    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_19_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
    '});
    0.52
    np
    0.49
    ResponseWriter
    0.47
    ukebox
    0.47
    imetable
    0.44
    ضغط
    0.44
    finally
    0.43
    cbind
    0.43
    });
    0.43
    Instrument
    0.43
    POSITIVE LOGITS
     ascetic
    0.57
     innervation
    0.52
     aton
    0.52
     divest
    0.51
     nihil
    0.50
     evanes
    0.50
     androgen
    0.50
     dispersal
    0.50
     ken
    0.49
     לא
    0.49
    Activations Density 0.000%

    No Known Activations