© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 966
    Prev
    Next
    INDEX
    Explanations

    work

    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_44_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
     Lem
    0.39
    чними
    0.39
    τικής
    0.38
    чним
    0.38
    磵
    0.38
     архівної
    0.38
    σιν
    0.37
     Alphabet
    0.37
     λε
    0.35
    fought
    0.35
    POSITIVE LOGITS
    ീല
    0.42
     deny
    0.41
     immunosupp
    0.38
     denials
    0.38
    耋
    0.38
     denying
    0.38
    СП
    0.38
    ี่ยน
    0.37
    ஜக
    0.37
    ínsula
    0.37
    Activations Density 0.020%

    No Known Activations