© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39259
    Prev
    Next
    INDEX
    Explanations

    camera equipment and mounting

    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_11_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
    I
    0.82
    R
    0.75
    S
    0.65
    D
    0.64
    N
    0.63
    K
    0.63
    H
    0.61
     model
    0.59
    AT
    0.59
    Nickel
    0.59
    POSITIVE LOGITS
     attribut
    0.61
    <unused700>
    0.60
     Eigenschaften
    0.59
    zeichnis
    0.57
    <unused650>
    0.57
    attform
    0.57
     *}\
    0.57
    erweise
    0.56
     zweiten
    0.55
     notor
    0.55
    Activations Density 0.011%

    No Known Activations