© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38936
    Prev
    Next
    INDEX
    Explanations

    HashiCorp products

    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
    大
    0.75
     відбувається
    0.66
    s
    0.65
    ের
    0.63
    <0x80>
    0.63
    一种
    0.62
    ある
    0.60
    の頃
    0.60
    中
    0.60
    一
    0.59
    POSITIVE LOGITS
    ir
    1.02
    ar
    0.98
    ul
    0.89
    oh
    0.86
    o
    0.86
     as
    0.80
     a
    0.80
    uit
    0.79
    world
    0.79
     .)
    0.79
    Activations Density 0.004%

    No Known Activations