© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10877
    Prev
    Next
    INDEX
    Explanations

    fish species and waste

    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_13_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
    ន្ធ
    0.15
    จะ
    0.15
    螅
    0.14
     alternatives
    0.14
    рии
    0.14
    стран
    0.14
     alterar
    0.14
    ками
    0.14
     crítica
    0.14
     оцен
    0.13
    POSITIVE LOGITS
     {
    0.18
    ({
    0.17
    {},
    0.17
     beneficia
    0.16
     }
    0.15
     {_
    0.15
     kapal
    0.15
    JH
    0.15
    દિવસ
    0.14
    Hv
    0.14
    Activations Density 0.011%

    No Known Activations