© 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. 249915
    Prev
    Next
    INDEX
    Explanations

    code or structure

    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
     theseKeys
    0.40
    ☘
    0.40
    ộp
    0.38
     sensation
    0.37
     silenced
    0.36
     lures
    0.36
    ologen
    0.36
    䤚
    0.36
    斛
    0.35
    arlock
    0.34
    POSITIVE LOGITS
    ন্দর
    0.36
     OR
    0.35
    OR
    0.35
     IS
    0.33
     IN
    0.32
    ದಲ್ಲ
    0.32
    TO
    0.32
     વિના
    0.31
    FOR
    0.31
    nto
    0.31
    Activations Density 0.046%

    No Known Activations