© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147239
    Prev
    Next
    INDEX
    Explanations

    Important Caveats First:**

    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_18_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
    Because
    0.30
    First
    0.30
    -
    0.29
     First
    0.28
    Service
    0.28
    y
    0.28
    Government
    0.27
                
    0.27
     Because
    0.27
    hundred
    0.27
    POSITIVE LOGITS
    ಿದ್ದೇನೆ
    0.28
     uniaxial
    0.26
     epitope
    0.26
     gemüt
    0.26
     jaunâtre
    0.26
    ི
    0.26
     rougeâtre
    0.26
     bebés
    0.25
     hypoth
    0.25
    ཥ
    0.25
    Activations Density 0.009%

    No Known Activations