© 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. 23131
    Prev
    Next
    INDEX
    Explanations

    Python docstrings

    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
    ================
    0.47
    ---------------
    0.44
    ……………………
    0.39
    ]}/${
    0.39
    [_
    0.39
    ++++++++++++++++
    0.37
    ————————————————
    0.37
    ----------------
    0.37
    ~~~~~~~~
    0.37
    Plays
    0.37
    POSITIVE LOGITS
     anteced
    0.40
     programm
    0.39
     program
    0.37
     snatched
    0.36
     contrasts
    0.35
    程序
    0.35
     ousted
    0.35
    <0x0D>
    0.35
     stole
    0.34
     trans
    0.34
    Activations Density 0.010%

    No Known Activations