© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209563
    Prev
    Next
    INDEX
    Explanations

    aid package debate

    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_20_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
    og
    0.49
    2
    0.44
     этот
    0.44
     factors
    0.43
     Factors
    0.40
     Gesellschaft
    0.39
     at
    0.39
    ilder
    0.39
     இந்தக்
    0.39
    ing
    0.38
    POSITIVE LOGITS
    ｙ
    0.44
     neces
    0.43
     ohms
    0.43
     принад
    0.43
    یتے
    0.42
    వా
    0.42
    autoarima
    0.41
     націона
    0.41
    󠁬
    0.41
     कंप्लीट
    0.40
    Activations Density 0.001%

    No Known Activations