© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169741
    Prev
    Next
    INDEX
    Explanations

    MD

    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_56_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
     manager
    0.50
    ².
    0.50
    ³.
    0.50
    °.
    0.49
     Manager
    0.49
    †
    0.48
    ..
    0.46
    *.
    0.46
    ^
    0.45
    <sup>
    0.45
    POSITIVE LOGITS
     Faces
    0.41
    หน้า
    0.40
     لد
    0.38
    Retour
    0.38
     وجه
    0.38
     لگتا
    0.36
    জিব
    0.36
    耻
    0.35
    ológicas
    0.35
    ের
    0.35
    Activations Density 0.000%

    No Known Activations