© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25656
    Prev
    Next
    INDEX
    Explanations

    full name, address, phone number

    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_10_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
     explores
    0.37
    !
    0.37
     roam
    0.35
     encontr
    0.34
     equ
    0.33
    ளையும்
    0.33
     previews
    0.33
     irons
    0.33
     removes
    0.33
     angles
    0.32
    POSITIVE LOGITS
    ments
    0.41
    bara
    0.39
    ២
    0.38
    bare
    0.37
    𝟐
    0.37
    ၂
    0.37
    एफ
    0.36
     Leclerc
    0.36
     :',
    0.36
    bank
    0.36
    Activations Density 0.128%

    No Known Activations