© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194973
    Prev
    Next
    INDEX
    Explanations

    IP addresses and file paths

    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
    consin
    0.40
     maxlength
    0.38
     wannan
    0.37
     quantification
    0.37
     vaid
    0.37
    \%)
    0.37
     nodded
    0.35
     vesting
    0.35
     detection
    0.35
     scopes
    0.35
    POSITIVE LOGITS
    锟
    0.43
    ancia
    0.43
    란
    0.41
     भेट
    0.40
    녀
    0.39
    dict
    0.38
    dem
    0.38
     وك
    0.38
    idem
    0.38
     მიმო
    0.38
    Activations Density 0.000%

    No Known Activations