© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20324
    Prev
    Next
    INDEX
    Explanations

    Help and directions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    アクション
    0.44
     Edmund
    0.39
     Coch
    0.39
     Francia
    0.38
     pund
    0.38
     Lune
    0.38
    賠
    0.37
     ಅನ
    0.36
     criticism
    0.36
     Luh
    0.36
    POSITIVE LOGITS
    слан
    0.43
    vestre
    0.42
    pan
    0.39
     धा
    0.39
    سل
    0.38
    ສະ
    0.38
    ั่ว
    0.36
    মার
    0.36
    सल
    0.36
    setBadgeText
    0.36
    Activations Density 0.049%

    No Known Activations