© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36765
    Prev
    Next
    INDEX
    Explanations

    Malaysia

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     K
    0.51
    ฟา
    0.45
    ßt
    0.43
    фа
    0.40
     cal
    0.38
    桦
    0.37
     رش
    0.37
    칼
    0.37
     दिनेश
    0.37
     denars
    0.37
    POSITIVE LOGITS
     Bend
    0.49
    тека
    0.47
     Bou
    0.45
    Bend
    0.44
     boul
    0.43
     Bant
    0.42
     Sims
    0.42
     Beckman
    0.41
     bou
    0.40
    Bou
    0.40
    Activations Density 0.002%

    No Known Activations