© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1470
    Prev
    Next
    INDEX
    Explanations

    analytical techniques and emerging fields

    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_39_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
     subs
    0.45
     Azul
    0.40
     identidade
    0.38
    憩
    0.37
    实验室
    0.36
     വീ
    0.36
     znam
    0.36
     subsistence
    0.36
     manusia
    0.36
    效
    0.36
    POSITIVE LOGITS
     nanotechnology
    0.59
    Nan
    0.59
     Nan
    0.58
    Novel
    0.56
     Analytical
    0.55
    Technologies
    0.55
    Analytical
    0.55
     nan
    0.54
     analytical
    0.54
     nonthermal
    0.53
    Activations Density 0.072%

    No Known Activations