© 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. 31649
    Prev
    Next
    INDEX
    Explanations

    list of items or descriptions

    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_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
    ]@
    0.40
     stalking
    0.38
     funerals
    0.38
     hunter
    0.38
     stalk
    0.34
     chasse
    0.34
    oney
    0.34
     enveloped
    0.33
     Servi
    0.33
     സാ
    0.33
    POSITIVE LOGITS
    linebreak
    0.45
     輸入
    0.43
     ग्लोबल
    0.38
     nargs
    0.38
    DOUT
    0.38
    椃
    0.38
     audiencia
    0.37
     रूट्स
    0.37
    主に
    0.36
    ಭಾವ
    0.36
    Activations Density 0.025%

    No Known Activations