© 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. 204294
    Prev
    Next
    INDEX
    Explanations

    AX, Value text segments

    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
     rares
    0.54
     regain
    0.46
     circul
    0.45
     pren
    0.44
     inflict
    0.44
     transmit
    0.43
    u
    0.43
     tongue
    0.43
     coverage
    0.43
     reap
    0.43
    POSITIVE LOGITS
    ㇁
    0.47
     Asociación
    0.46
     आवश्यकता
    0.46
     المنا
    0.46
    ٨
    0.46
    요
    0.45
     Departamento
    0.43
    ،
    0.43
     كرد
    0.42
     ،
    0.42
    Activations Density 0.000%

    No Known Activations