© 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. 180968
    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
     Shir
    0.49
    ushan
    0.48
     Po
    0.44
    ates
    0.44
    㫣
    0.44
     Sco
    0.44
     Lieb
    0.43
     गुणन
    0.42
     llevando
    0.42
    ars
    0.42
    POSITIVE LOGITS
    NCc
    0.53
    Concepts
    0.52
    ጣ
    0.51
     schm
    0.51
    πτυ
    0.50
     concepts
    0.50
    Rules
    0.48
    好き
    0.48
    вища
    0.48
    concepts
    0.48
    Activations Density 0.000%

    No Known Activations