© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163687
    Prev
    Next
    INDEX
    Explanations

    Handoff

    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_13_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
     marvellous
    0.26
     fantastic
    0.26
    B
    0.26
     Argentine
    0.24
    旂
    0.24
    𝓑
    0.24
     osobow
    0.24
    D
    0.23
    ہے
    0.23
     prerogative
    0.23
    POSITIVE LOGITS
    odal
    0.27
    odor
    0.27
     있다
    0.26
    atin
    0.26
     t
    0.26
    adan
    0.25
     solub
    0.25
    eteor
    0.24
     Nadal
    0.24
    ete
    0.24
    Activations Density 0.002%

    No Known Activations