© 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. 23537
    Prev
    Next
    INDEX
    Explanations

    version

    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
     ##
    0.45
     poł
    0.39
     quantos
    0.38
     Drone
    0.37
     eder
    0.36
     சார்ப
    0.36
    HIDE
    0.36
     Juliana
    0.36
     ẩn
    0.35
     가운데
    0.34
    POSITIVE LOGITS
    =(\
    0.42
    }=(\
    0.39
    =(
    0.39
    filled
    0.38
    Versions
    0.38
    Version
    0.38
    }=\{\
    0.38
    Mental
    0.38
    Buildings
    0.37
    ाने
    0.37
    Activations Density 0.000%

    No Known Activations