© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195145
    Prev
    Next
    INDEX
    Explanations

    that is

    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_27_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
    Ἥ
    0.37
    স্য
    0.35
    बन
    0.32
     plateau
    0.32
    רא
    0.31
     simulated
    0.31
    уы
    0.31
    Į
    0.31
    atelle
    0.30
    Domain
    0.30
    POSITIVE LOGITS
     evidente
    0.38
     samtidig
    0.36
    certificates
    0.35
     reparations
    0.35
     politico
    0.34
    源代码
    0.34
     papers
    0.34
     имуще
    0.33
     situatie
    0.33
     fiecare
    0.33
    Activations Density 0.003%

    No Known Activations