© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42460
    Prev
    Next
    INDEX
    Explanations

    numbers relating to counts

    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_22_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
     poorly
    0.45
    klar
    0.44
     ఎలా
    0.43
     cleared
    0.42
    <0xA1>
    0.42
     Ş
    0.41
     severely
    0.41
     whe
    0.41
     uncomfortable
    0.41
     काफी
    0.41
    POSITIVE LOGITS
     насеко
    0.40
    )=$
    0.38
    ierrez
    0.38
     organismos
    0.37
     eastern
    0.37
    ྥ
    0.36
    《
    0.36
     восто
    0.35
     dimensiones
    0.35
     vých
    0.35
    Activations Density 0.003%

    No Known Activations