© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208356
    Prev
    Next
    INDEX
    Explanations

    code programming language implementations

    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_20_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
    instrument
    0.29
    }$&$-
    0.25
    convers
    0.25
    Convers
    0.25
     énergétique
    0.25
    zzle
    0.24
    quando
    0.24
    zip
    0.24
    ':'
    0.24
    keys
    0.24
    POSITIVE LOGITS
     polysaccharide
    0.28
     sailing
    0.27
    ஸ்க
    0.26
     Pinot
    0.26
    毅
    0.26
     inicial
    0.25
     whaling
    0.25
     skiing
    0.25
     первые
    0.25
     aired
    0.25
    Activations Density 0.003%

    No Known Activations