© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151670
    Prev
    Next
    INDEX
    Explanations

    So

    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_59_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
     go
    0.47
    go
    0.47
     drifts
    0.39
     really
    0.38
     wear
    0.38
    Go
    0.37
     trident
    0.36
    煥
    0.36
     act
    0.35
     vives
    0.35
    POSITIVE LOGITS
    elize
    0.45
     Believe
    0.44
    believe
    0.44
     Include
    0.42
    ですよね
    0.40
     Build
    0.40
     сказать
    0.40
     Indicate
    0.40
    are
    0.39
    bells
    0.39
    Activations Density 0.002%

    No Known Activations