© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201660
    Prev
    Next
    INDEX
    Explanations

    problem question

    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_46_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
     dict
    0.41
     signIn
    0.38
     Chapter
    0.35
    Cannot
    0.35
    蜥
    0.35
     Mout
    0.35
     Gradient
    0.34
    クサ
    0.34
    遌
    0.34
    变更
    0.33
    POSITIVE LOGITS
    itals
    0.48
     supervised
    0.42
     actually
    0.40
    োহর
    0.39
     đọc
    0.39
     talk
    0.39
    成績
    0.38
    話を
    0.38
    ნა
    0.38
    답
    0.38
    Activations Density 0.008%

    No Known Activations