© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
     ponctué
    0.50
    ərd
    0.46
    ሉም
    0.44
    inputFields
    0.43
    }:=
    0.43
    ිනි
    0.43
    랍
    0.43
     heralded
    0.43
    桝
    0.42
    unicode
    0.42
    POSITIVE LOGITS
    Seems
    0.51
     erzählen
    0.48
    GO
    0.46
    Freedom
    0.45
    itization
    0.45
    யம்
    0.45
    علم
    0.45
    Deaths
    0.44
    Holds
    0.44
    В
    0.43
    Activations Density 0.000%

    No Known Activations