© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31543
    Prev
    Next
    INDEX
    Explanations

    dramatic sky

    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_31_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
     അന്ന
    0.35
    तत्
    0.34
    unam
    0.34
     fouled
    0.34
    紳
    0.33
     retro
    0.33
     giggle
    0.33
     убы
    0.33
    訕
    0.33
     spinoff
    0.32
    POSITIVE LOGITS
     Poet
    0.39
     audioElement
    0.37
    Segments
    0.36
     เสียง
    0.35
     Dramatic
    0.35
    Scenic
    0.35
    仞
    0.35
     dramatic
    0.35
     xj
    0.34
    Authenticator
    0.34
    Activations Density 0.038%

    No Known Activations