© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35741
    Prev
    Next
    INDEX
    Explanations

    opening brackets

    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_50_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
     An
    1.42
    An
    1.19
     anod
    0.87
     안
    0.86
    安
    0.86
     anode
    0.80
     anis
    0.80
     Anu
    0.79
     anem
    0.78
     ANO
    0.77
    POSITIVE LOGITS
     ...]
    0.60
    …]
    0.59
    !]
    0.59
    ...]
    0.57
    sic
    0.57
    ,]
    0.55
     sic
    0.55
    ?]
    0.53
    +]
    0.50
    .]
    0.49
    Activations Density 0.011%

    No Known Activations