© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89441
    Prev
    Next
    INDEX
    Explanations

    molecules

    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_23_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
    ണ്ഡി
    0.42
    ಗಳಿಂದ
    0.40
    ༸
    0.40
    炙
    0.38
     proposent
    0.38
    জনক
    0.37
    PhotoButton
    0.37
    දර
    0.37
    的工作
    0.37
     offrir
    0.37
    POSITIVE LOGITS
    По
    0.49
    %).
    0.43
    finally
    0.43
    def
    0.41
    За
    0.41
    arach
    0.40
    maintain
    0.40
    विड
    0.40
    ').
    0.40
    kubectl
    0.39
    Activations Density 0.002%

    No Known Activations