© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122273
    Prev
    Next
    INDEX
    Explanations

    Franklin, Mell, Mira, Olympus

    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_3_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
    s
    0.63
            
    0.63
    ach
    0.58
    is
    0.55
    ass
    0.55
     type
    0.54
    ä
    0.54
     tripartite
    0.54
    id
    0.53
     adopt
    0.52
    POSITIVE LOGITS
    。
    0.69
    ，
    0.63
    ။
    0.61
    ۔
    0.59
    ۳
    0.59
    خری
    0.57
    کی
    0.56
    علی
    0.56
    HO
    0.55
    ።
    0.55
    Activations Density 0.000%

    No Known Activations