© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175466
    Prev
    Next
    INDEX
    Explanations

    cracks

    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_20_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
     പ്രസിഡ
    0.54
     ஆர
    0.49
     প্রাস
    0.47
     bä
    0.47
     Macht
    0.47
    <unused33>
    0.46
     kte
    0.46
    excludeFolder
    0.45
     $\%$
    0.44
     Rutland
    0.44
    POSITIVE LOGITS
    led
    0.53
    Tim
    0.52
    ":
    0.49
    is
    0.49
    "
    0.48
    TIM
    0.48
    who
    0.48
    ::
    0.47
    with
    0.47
    T
    0.46
    Activations Density 0.001%

    No Known Activations