© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208854
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    тие
    0.48
    тей
    0.46
    မှာ
    0.42
     контек
    0.41
    დას
    0.41
    ч
    0.41
    ー
    0.41
     celebrates
    0.40
    మన
    0.40
     సందర్భ
    0.40
    POSITIVE LOGITS
    immä
    0.52
     améli
    0.48
     völl
    0.47
     logement
    0.46
    Indirect
    0.45
     humain
    0.45
    InsertInt
    0.44
     anderen
    0.44
     ensl
    0.44
    始
    0.44
    Activations Density 0.000%

    No Known Activations