© 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
    2. Gemma-3-27B-IT
    3. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99250
    Prev
    Next
    INDEX
    Explanations

    escape from reality

    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_14_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
    nuts
    0.13
    dued
    0.12
    Q
    0.11
    H
    0.11
    boot
    0.11
    rule
    0.11
    etal
    0.11
     ($
    0.11
    done
    0.11
    IRQ
    0.11
    POSITIVE LOGITS
     paisajes
    0.11
     Buddhist
    0.11
     остро
    0.11
    医
    0.11
    淼
    0.11
     Literacy
    0.10
     Tuttle
    0.10
     Story
    0.10
     нагре
    0.10
     Medical
    0.10
    Activations Density 0.022%

    No Known Activations