© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200874
    Prev
    Next
    INDEX
    Explanations

    rise of

    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_6_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
     to
    0.85
    gunakan
    0.81
    ata
    0.79
    ן
    0.79
    ry
    0.78
    iden
    0.78
    àn
    0.75
     by
    0.75
    ha
    0.75
    är
    0.71
    POSITIVE LOGITS
     уви
    0.86
    on
    0.80
     оформления
    0.79
     оружия
    0.79
     пациен
    0.78
     médica
    0.77
     aliv
    0.77
    <unused60>
    0.76
    .
    0.75
     immobili
    0.75
    Activations Density 0.001%

    No Known Activations