© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84156
    Prev
    Next
    INDEX
    Explanations

    Rust impl blocks

    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_23_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
     ಖರೀ
    0.49
    urchase
    0.48
    sqlUpdate
    0.48
    買
    0.47
     thanking
    0.46
    धपुर
    0.46
    izzate
    0.46
    Annual
    0.46
     ಬರುತ್ತ
    0.46
     anual
    0.45
    POSITIVE LOGITS
     Parish
    0.40
     observable
    0.38
     entropy
    0.38
     prostředí
    0.37
     environments
    0.37
    畜
    0.37
     “
    0.36
     evalu
    0.35
     energetics
    0.35
    煎
    0.35
    Activations Density 0.000%

    No Known Activations