© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171726
    Prev
    Next
    INDEX
    Explanations

    styles applied

    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_20_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
     Honda
    0.43
     excellente
    0.42
     Hond
    0.41
     compiling
    0.41
     dizendo
    0.40
     Oggi
    0.39
    ሏ
    0.39
     quase
    0.38
     Ecco
    0.38
     Garmin
    0.38
    POSITIVE LOGITS
    Response
    0.39
    译
    0.38
    RESOURCE
    0.37
    IDUAL
    0.37
    Temperature
    0.37
    developed
    0.37
    温度
    0.36
    ActionsCallback
    0.36
    YES
    0.36
    সুল
    0.36
    Activations Density 0.002%

    No Known Activations