Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260554
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    y
    1.26
     ac
    1.16
     inv
    1.15
     alright
    1.11
    ering
    1.07
     olan
    1.02
     ś
    1.01
    ा
    1.00
     hö
    1.00
     consec
    1.00
    POSITIVE LOGITS
     vibhav
    1.30
    <unused143>
    1.30
    <unused564>
    1.29
    <unused302>
    1.28
    Linkedin
    1.28
    <unused626>
    1.28
     pushedAt
    1.27
    MathMarks
    1.26
    <0xDE>
    1.26
    calories
    1.25
    Activations Density 0.000%

    No Known Activations