© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194517
    Prev
    Next
    INDEX
    Explanations

    fire, burn, or degree

    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_15_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
    ṇa
    0.52
    iteľ
    0.52
    batas
    0.50
    łą
    0.50
    łączy
    0.50
    șa
    0.49
    ņ
    0.49
    ži
    0.49
     совершенно
    0.49
    ça
    0.49
    POSITIVE LOGITS
    রন
    0.54
     eye
    0.49
    西
    0.48
    桐
    0.47
    ovina
    0.46
     strategic
    0.45
    鿌
    0.44
    光
    0.44
    汤
    0.44
    凌
    0.44
    Activations Density 0.000%

    No Known Activations