© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172754
    Prev
    Next
    INDEX
    Explanations

    historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     luminoso
    0.46
     odour
    0.44
    掃除
    0.44
     সরাস
    0.43
     obligado
    0.43
    嬗
    0.43
    tembre
    0.42
     wry
    0.42
     अनलि
    0.42
     लापता
    0.42
    POSITIVE LOGITS
    س
    0.40
    net
    0.38
    gameState
    0.38
    t
    0.37
    league
    0.37
     political
    0.37
    ına
    0.37
    ının
    0.36
    áž
    0.36
    的問題
    0.36
    Activations Density 0.008%

    No Known Activations