© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57280
    Prev
    Next
    INDEX
    Explanations

    Cyprus

    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_11_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
     reactor
    0.25
     inexist
    0.25
     mutant
    0.25
    abhuto
    0.25
    ა
    0.25
     downloader
    0.25
     compound
    0.25
     offender
    0.25
     signatory
    0.25
     volcano
    0.24
    POSITIVE LOGITS
    I
    0.29
    This
    0.28
    When
    0.27
    O
    0.27
     Utilize
    0.26
    1
    0.26
    It
    0.26
    Use
    0.26
    Petit
    0.26
    Who
    0.25
    Activations Density 0.003%

    No Known Activations