© 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. 170213
    Prev
    Next
    INDEX
    Explanations

    Read

    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
     bag
    0.45
     or
    0.43
     bog
    0.43
     bags
    0.42
    或
    0.38
     или
    0.38
     அல்லது
    0.38
     ወይም
    0.38
     किंवा
    0.37
     或
    0.37
    POSITIVE LOGITS
    Graphic
    0.44
     deeply
    0.42
     பேரு
    0.40
    Ӹ
    0.40
     Pohl
    0.40
     *}(
    0.39
     tramite
    0.38
    राला
    0.37
    }+{
    0.37
    ᴙ
    0.36
    Activations Density 0.002%

    No Known Activations