© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203693
    Prev
    Next
    INDEX
    Explanations

    testing boundaries

    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_25_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
     (^{
    0.25
    ␶
    0.25
    вшей
    0.25
     tahan
    0.25
    懾
    0.24
    <code>
    0.24
     पाओ
    0.24
     inconce
    0.24
    ங்கும்
    0.24
    лл
    0.23
    POSITIVE LOGITS
     mild
    0.28
     لدى
    0.27
     όσο
    0.27
     NOT
    0.27
     குறைக்க
    0.26
     Dixon
    0.26
     বজায়
    0.26
     Natura
    0.26
     listopadu
    0.26
    半
    0.26
    Activations Density 0.014%

    No Known Activations