© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206974
    Prev
    Next
    INDEX
    Explanations

    separate, wing, divisions, private, connecting

    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
    /(
    0.42
     molten
    0.38
     porosity
    0.37
     infusion
    0.36
    LB
    0.36
     workmanship
    0.35
    PL
    0.34
    คง
    0.34
     취
    0.34
     taste
    0.34
    POSITIVE LOGITS
     fondo
    0.45
     diferite
    0.44
     delen
    0.44
    aadhar
    0.43
     serangan
    0.41
    令牌
    0.40
     andere
    0.40
     ટુ
    0.40
     aplicativo
    0.39
     verschillende
    0.39
    Activations Density 0.000%

    No Known Activations