© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12349
    Prev
    Next
    INDEX
    Explanations

    bandit problem

    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_13_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
    ’
    0.53
     ע
    0.45
     imp
    0.44
    Mud
    0.43
     מע
    0.42
     se
    0.42
     став
    0.42
     מיי
    0.42
     ye
    0.42
    
    0.41
    POSITIVE LOGITS
     Blvd
    0.47
     behind
    0.45
    andelion
    0.42
     Behind
    0.41
    ッジ
    0.40
    ahooks
    0.40
     Corners
    0.39
    పర్
    0.38
    ahassee
    0.38
     Maschine
    0.38
    Activations Density 0.050%

    No Known Activations