© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195791
    Prev
    Next
    INDEX
    Explanations

    This

    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_26_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
    so
    0.29
    $).
    0.26
    signal
    0.26
    innam
    0.25
    star
    0.25
     uspe
    0.24
    by
    0.24
    bir
    0.24
    string
    0.24
    dialog
    0.24
    POSITIVE LOGITS
    监管
    0.27
    舵
    0.27
    Servo
    0.26
    ियार
    0.25
     nemoc
    0.25
    ]++;
    0.24
     moteurs
    0.23
    颦
    0.23
     moteur
    0.23
    防治
    0.23
    Activations Density 0.006%

    No Known Activations