© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163402
    Prev
    Next
    INDEX
    Explanations

    instructions for action

    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_31_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
    ल्ला
    0.30
     Eligibility
    0.29
    爨
    0.29
     multilingual
    0.29
    ègre
    0.29
     CDS
    0.29
     WEL
    0.29
     umano
    0.28
     kafka
    0.28
     cad
    0.28
    POSITIVE LOGITS
    ivative
    0.36
    Pressure
    0.35
    兖
    0.33
    itoneal
    0.33
    Command
    0.32
    iply
    0.32
    Bruce
    0.32
    Dev
    0.31
    umeric
    0.31
    Squ
    0.31
    Activations Density 0.001%

    No Known Activations