© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37131
    Prev
    Next
    INDEX
    Explanations

    place names and input code

    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_11_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
    魧
    0.69
     жүкт
    0.64
    🥒
    0.64
    楖
    0.63
     thisobject
    0.63
    䣮
    0.62
    𝟮
    0.62
    㜿
    0.62
    碖
    0.61
    𝘾
    0.61
    POSITIVE LOGITS
    <0x0D>
    0.82
    f
    0.73
     F
    0.72
    6
    0.69
    ag
    0.69
    ↵
    0.68
    am
    0.68
    ge
    0.68
    da
    0.67
    5
    0.67
    Activations Density 0.008%

    No Known Activations