© 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. 155422
    Prev
    Next
    INDEX
    Explanations

    of

    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
    type
    0.55
     and
    0.48
     art
    0.45
    _
    0.45
    far
    0.43
    tools
    0.41
    fitness
    0.39
    town
    0.39
    finder
    0.39
     và
    0.39
    POSITIVE LOGITS
    M
    0.44
    鈥
    0.44
    ibe
    0.40
    Ã
    0.39
    ২১
    0.39
    VICES
    0.38
    AJ
    0.38
    лке
    0.38
    JX
    0.38
    igus
    0.37
    Activations Density 0.001%

    No Known Activations