© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24509
    Prev
    Next
    INDEX
    Explanations

    (

    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
     String
    0.39
    𝑂
    0.39
    String
    0.38
    SEVERE
    0.38
     GoObject
    0.38
    ],'
    0.37
    }{$
    0.37
    ！】
    0.37
    \}$.
    0.36
    \}$,
    0.36
    POSITIVE LOGITS
     alert
    0.40
     contest
    0.37
    Alert
    0.34
    oros
    0.34
    ისი
    0.32
    ۵
    0.32
     meas
    0.32
    ५
    0.32
    快捷
    0.31
     grown
    0.31
    Activations Density 0.003%

    No Known Activations