© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246613
    Prev
    Next
    INDEX
    Explanations

    opportunities and professional development

    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_40_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
     hossz
    0.43
     cubic
    0.41
     wearing
    0.38
     trening
    0.38
     화학
    0.38
     duit
    0.37
     #:
    0.37
     экза
    0.37
    itación
    0.37
    珩
    0.37
    POSITIVE LOGITS
    Corporate
    0.40
     corporates
    0.39
     convenient
    0.39
    便利な
    0.38
    PH
    0.36
    }=(
    0.36
    corporate
    0.36
    ARE
    0.35
    Are
    0.34
    떨
    0.34
    Activations Density 0.000%

    No Known Activations