© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159645
    Prev
    Next
    INDEX
    Explanations

    cer words ending in -osion or -eading

    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_2_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
    ENT
    1.27
    AME
    1.13
    રા
    1.07
    Funcion
    1.05
    י
    1.05
    OCK
    1.03
    ມັນ
    1.03
    들이
    1.02
    GRAD
    1.00
    speakers
    1.00
    POSITIVE LOGITS
    il
    1.55
    ing
    1.34
    v
    1.30
     by
    1.16
    ist
    1.15
    ens
    1.11
    em
    1.08
    en
    1.07
    ot
    1.07
    ਾ
    1.06
    Activations Density 0.006%

    No Known Activations