© 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. 1949
    Prev
    Next
    INDEX
    Explanations

    behind

    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
    гө
    0.44
     छोर
    0.38
    鑑
    0.38
    petal
    0.38
     Loew
    0.37
    tes
    0.37
    évrier
    0.37
    𝑫
    0.37
    唋
    0.37
    icit
    0.36
    POSITIVE LOGITS
     room
    0.49
    室
    0.46
    room
    0.43
     stra
    0.43
     Room
    0.42
     społec
    0.41
    で作
    0.41
     ROOM
    0.41
    Room
    0.40
     STREET
    0.40
    Activations Density 0.004%

    No Known Activations