© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91011
    Prev
    Next
    INDEX
    Explanations

    display manager

    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_3_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
     be
    0.91
     as
    0.77
    很
    0.65
    精神
    0.64
     practitioner
    0.64
    м
    0.63
     pressur
    0.62
    一个
    0.62
    ம்
    0.60
     ,
    0.59
    POSITIVE LOGITS
     Keci
    0.70
    Acknowledg
    0.68
     Estimate
    0.64
    itters
    0.63
     Quar
    0.63
    RENDITION
    0.62
    Nur
    0.62
    strukt
    0.62
    a
    0.62
    ه
    0.62
    Activations Density 0.006%

    No Known Activations