© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61384
    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_59_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
    Dio
    0.43
    Co
    0.42
    Ε
    0.41
    per
    0.40
    B
    0.40
    Chi
    0.40
    Po
    0.39
    player
    0.39
    >(
    0.38
    >";
    0.38
    POSITIVE LOGITS
     Lorsque
    0.46
     Goes
    0.41
     Nghi
    0.41
    -
    0.41
    देशीर
    0.41
    inata
    0.40
    തന്നെ
    0.40
     века
    0.39
    챗
    0.39
     attrs
    0.39
    Activations Density 0.000%

    No Known Activations