© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22061
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    <0xC2>
    0.11
    say
    0.09
    input
    0.08
    </
    0.08
     say
    0.08
     Scary
    0.08
     sinister
    0.08
    Â
    0.08
    or
    0.08
     Opportunity
    0.08
    POSITIVE LOGITS
     لائن
    0.09
     አይ
    0.08
     anodes
    0.08
    ێر
    0.08
     zippers
    0.08
    线的
    0.08
     lenses
    0.08
     ribs
    0.08
     encoders
    0.08
    IFIER
    0.08
    Activations Density 0.336%

    No Known Activations