© 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. 161858
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
     –
    0.53
     -
    0.48
    –
    0.44
    :
    0.43
     jiné
    0.41
    стане
    0.39
     potest
    0.39
    ・
    0.38
    -‘
    0.37
    čni
    0.37
    POSITIVE LOGITS
    INFORMATION
    0.37
     blinded
    0.36
    дова
    0.33
     phony
    0.32
     observe
    0.32
     పద
    0.32
     informations
    0.32
     blindness
    0.32
    அந்த
    0.32
    arean
    0.32
    Activations Density 0.021%

    No Known Activations