© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150484
    Prev
    Next
    INDEX
    Explanations

    database connection

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    .
    0.94
    **.
    0.63
    [],
    0.52
    .**
    0.51
    ('').
    0.51
    ².
    0.51
    ®.
    0.50
    '.
    0.50
    _
    0.50
    ['
    0.50
    POSITIVE LOGITS
    :
    0.50
     Precio
    0.48
     escultura
    0.45
     Gobierno
    0.44
     Cómo
    0.43
     করবার
    0.43
    ៖
    0.43
     Calendar
    0.42
     পদ্ধতি
    0.42
     multiplicación
    0.42
    Activations Density 0.005%

    No Known Activations