© 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. 20833
    Prev
    Next
    INDEX
    Explanations

    dol

    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
    哦
    0.38
    Oh
    0.35
    ∽
    0.35
     Pr
    0.34
     Ear
    0.34
    مرار
    0.34
    ]]);
    0.33
     適
    0.33
    pr
    0.33
     ${_
    0.33
    POSITIVE LOGITS
    돌
    0.90
    순
    0.55
    доль
    0.50
    DOL
    0.50
    dol
    0.47
    둥
    0.46
    ddot
    0.45
     dol
    0.44
     돌
    0.42
    ドル
    0.41
    Activations Density 0.007%

    No Known Activations