© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201560
    Prev
    Next
    INDEX
    Explanations

    they say

    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_12_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
    ın
    0.75
     apie
    0.59
     nickname
    0.58
    의
    0.57
     rued
    0.57
    s
    0.57
     about
    0.54
     reiv
    0.54
    の
    0.54
    าน
    0.53
    POSITIVE LOGITS
    Hope
    0.59
     శక్తి
    0.59
    োগান
    0.58
    arger
    0.55
    illion
    0.55
     Hope
    0.54
    atiti
    0.54
    abby
    0.54
    śa
    0.53
    ulsion
    0.52
    Activations Density 0.001%

    No Known Activations