© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195215
    Prev
    Next
    INDEX
    Explanations

    0 to N-1 ranges

    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_27_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
     inexpensive
    0.40
     Rhet
    0.39
    compare
    0.39
    rell
    0.39
     behold
    0.38
     compare
    0.37
     種
    0.37
    ern
    0.36
     оса
    0.36
     };
    0.36
    POSITIVE LOGITS
     WAVE
    0.43
     joints
    0.39
     GOODS
    0.38
    AVG
    0.37
     DOB
    0.37
    FZ
    0.37
     Joints
    0.37
    頩
    0.37
    霞
    0.36
     VG
    0.36
    Activations Density 0.001%

    No Known Activations