© 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. 176272
    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
    Ally
    0.49
    A
    0.49
     Ally
    0.46
    OMX
    0.46
    น์
    0.45
     subtleties
    0.45
    I
    0.45
    ↡
    0.45
     quatern
    0.44
    )、
    0.44
    POSITIVE LOGITS
     doigts
    0.54
     trabalhadores
    0.50
     passada
    0.49
    оборот
    0.48
    rador
    0.48
     কুকুর
    0.48
     அழுத்த
    0.48
     બહાર
    0.48
     Союз
    0.48
     Ке
    0.47
    Activations Density 0.000%

    No Known Activations