© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170480
    Prev
    Next
    INDEX
    Explanations

    closed source

    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
    C
    0.40
    Oh
    0.40
    Workflow
    0.39
    Kant
    0.38
    OH
    0.38
    Dihydro
    0.37
    That
    0.37
    He
    0.36
    icum
    0.36
    숫
    0.36
    POSITIVE LOGITS
     close
    0.54
    Close
    0.49
     Close
    0.47
     CLOSE
    0.45
     proches
    0.43
    CLOSE
    0.42
     proche
    0.41
    avez
    0.40
    ูน
    0.40
    …]
    0.38
    Activations Density 0.001%

    No Known Activations