© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252451
    Prev
    Next
    INDEX
    Explanations

    ability capacity

    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_56_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
     z
    0.50
    当
    0.50
     체
    0.43
     з
    0.42
    作
    0.41
    當
    0.40
    体
    0.40
     当
    0.38
     যখন
    0.38
    体的
    0.38
    POSITIVE LOGITS
    刚
    0.45
    剛
    0.44
    Tight
    0.42
     Tight
    0.39
     tight
    0.38
     Rig
    0.38
    completion
    0.38
    tight
    0.37
     Constitu
    0.37
    更有
    0.36
    Activations Density 0.001%

    No Known Activations