© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124078
    Prev
    Next
    INDEX
    Explanations

    leading zeros or start of hex

    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_37_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
     datatype
    0.42
     banner
    0.42
     dysph
    0.41
     reson
    0.40
     footer
    0.40
     swallowing
    0.40
    Timestamp
    0.39
    帯
    0.39
     Karam
    0.39
    കര
    0.39
    POSITIVE LOGITS
    glVertex
    0.35
    ATTR
    0.34
    putExtra
    0.34
     вз
    0.33
     пари
    0.33
    rawn
    0.33
    polymer
    0.33
     DIR
    0.33
    ゾート
    0.33
     поради
    0.32
    Activations Density 0.002%

    No Known Activations