© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52289
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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_55_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
     slowly
    0.42
     }}$,
    0.41
    衩
    0.40
     "..
    0.39
     },
    0.38
    ()}')
    0.38
     siRNA
    0.38
     }}
    0.38
     ん
    0.37
    anone
    0.37
    POSITIVE LOGITS
    健全
    0.48
    typename
    0.41
    ―
    0.40
    —
    0.39
    Percentage
    0.39
    At
    0.39
    Brun
    0.39
    STOCK
    0.38
    Unity
    0.38
    APPLICATION
    0.37
    Activations Density 0.004%

    No Known Activations