© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142255
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ।.
    0.43
     मोठी
    0.38
     generating
    0.38
    ovski
    0.37
     μή
    0.37
    -(\
    0.37
    古屋
    0.36
     overhead
    0.36
    ਜ
    0.36
    ieurs
    0.36
    POSITIVE LOGITS
     curriculum
    0.42
     Curriculum
    0.40
     enriched
    0.39
     enriching
    0.39
    បន្ថ
    0.38
    提升
    0.38
     implementation
    0.37
    成都
    0.36
     curricula
    0.36
     Mathias
    0.36
    Activations Density 0.001%

    No Known Activations