© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52638
    Prev
    Next
    INDEX
    Explanations

    Never hardcode

    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_55_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
    entie
    0.40
     పర
    0.38
     degeneration
    0.36
    酵
    0.35
    腊
    0.35
    वीन
    0.35
    뽕
    0.35
     Minority
    0.34
    ucar
    0.34
     作
    0.34
    POSITIVE LOGITS
     hard
    0.73
    hard
    0.59
    Hard
    0.53
     accident
    0.51
    accident
    0.50
     secures
    0.46
    HARD
    0.45
     HARD
    0.45
     share
    0.44
     redist
    0.44
    Activations Density 0.006%

    No Known Activations