© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36192
    Prev
    Next
    INDEX
    Explanations

    second chance attempt

    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_3_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
    -
    0.83
    )
    0.73
    ன்
    0.69
    the
    0.69
    an
    0.65
    }
    0.65
    珺
    0.64
     riche
    0.62
    ol
    0.61
    西哥
    0.60
    POSITIVE LOGITS
     to
    1.19
     at
    0.81
     radiographs
    0.71
    ப்ப
    0.70
    ח
    0.69
     for
    0.68
     gradients
    0.67
     syringes
    0.67
     shutdowns
    0.67
    م
    0.67
    Activations Density 0.005%

    No Known Activations