© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120349
    Prev
    Next
    INDEX
    Explanations

    company names

    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
    ଛ
    0.37
    ¾
    0.35
    Permission
    0.35
    apiRequest
    0.35
    नीचर
    0.35
    носить
    0.35
    Jan
    0.35
    ঞ্জ
    0.34
    Measurement
    0.34
    нього
    0.34
    POSITIVE LOGITS
     Tower
    0.54
     tower
    0.53
     뽑
    0.46
    Tower
    0.44
     towers
    0.43
     finishing
    0.43
     Fan
    0.43
     Induction
    0.42
     Capítulo
    0.42
     metaphorical
    0.41
    Activations Density 0.003%

    No Known Activations