© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69251
    Prev
    Next
    INDEX
    Explanations

    при

    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_51_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
     occult
    0.43
    )]$
    0.43
    omaly
    0.42
     Polo
    0.42
     polo
    0.42
    apa
    0.40
     Oxy
    0.40
     Mene
    0.40
     pel
    0.40
     tul
    0.39
    POSITIVE LOGITS
    andang
    0.44
    တိုင်း
    0.44
    pointers
    0.39
    ckpt
    0.39
    뎃
    0.39
    anda
    0.38
     Yankees
    0.38
    clicks
    0.38
    ICS
    0.37
     clowns
    0.37
    Activations Density 0.000%

    No Known Activations