© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206408
    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
    هاي
    0.44
    넣
    0.41
    های
    0.39
    ها
    0.38
    گذ
    0.37
    هم
    0.36
    않
    0.35
    "...
    0.35
    üss
    0.35
    (_
    0.34
    POSITIVE LOGITS
    —”
    0.43
    ‐
    0.42
     _{\
    0.41
    —“
    0.41
     ค่ะ
    0.40
    억원
    0.40
    ‑
    0.39
    amse
    0.39
    ونت
    0.39
     LikeLike
    0.38
    Activations Density 0.001%

    No Known Activations