© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7515
    Prev
    Next
    INDEX
    Explanations

    Class or tranche designations

    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_40_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
     paying
    0.38
    ENS
    0.38
     enforce
    0.37
     créée
    0.37
     এদেশে
    0.36
    銀
    0.36
    aira
    0.35
     страда
    0.35
    Absent
    0.35
     payable
    0.35
    POSITIVE LOGITS
    ंदी
    0.41
     لیون
    0.39
     मोड
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.37
     ไหม
    0.37
    훈련
    0.37
     nødv
    0.36
     paramInt
    0.36
    ◘
    0.36
    JTextField
    0.35
    Activations Density 0.021%

    No Known Activations