© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35690
    Prev
    Next
    INDEX
    Explanations

    firebase initialization

    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_31_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
    }^{*}=
    0.40
    }:${
    0.38
    🕌
    0.38
    україн
    0.37
    ୪
    0.36
     سسٹم
    0.36
    ध्याय
    0.35
    国道
    0.35
     clavier
    0.35
    敎
    0.35
    POSITIVE LOGITS
     contamin
    0.47
    hores
    0.47
    itiveness
    0.42
     olok
    0.41
     ha
    0.38
     contaminants
    0.38
    aling
    0.37
    Engine
    0.37
    jer
    0.37
    Be
    0.37
    Activations Density 0.002%

    No Known Activations