© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220955
    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_31_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
    Maximize
    0.42
    akura
    0.38
    ƒ
    0.38
    Objectives
    0.37
    渦
    0.37
    వై
    0.37
    Cit
    0.36
    成像
    0.36
    혜
    0.36
     rings
    0.35
    POSITIVE LOGITS
     enterr
    0.38
     quais
    0.38
    LOAD
    0.37
    परेशन
    0.37
    签约
    0.36
    ENT
    0.36
    ്ല
    0.36
     एंट
    0.36
    कॉ
    0.36
     faites
    0.35
    Activations Density 0.000%

    No Known Activations