© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 51624
    Prev
    Next
    INDEX
    Explanations

    ve

    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
     통해서
    0.39
    chnet
    0.39
     uncovered
    0.38
     sekal
    0.38
     ascertained
    0.38
     outraged
    0.37
     outlined
    0.37
    <unused18>
    0.37
     thrilled
    0.36
     ہونے
    0.36
    POSITIVE LOGITS
     specifically
    0.51
     stuck
    0.51
    specifically
    0.47
     específicamente
    0.46
    Specifically
    0.46
     done
    0.46
     Specifically
    0.45
    done
    0.43
    DONE
    0.42
     DONE
    0.41
    Activations Density 0.020%

    No Known Activations