© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101137
    Prev
    Next
    INDEX
    Explanations

    **strongly typed**

    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_16_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
    i
    0.31
     New
    0.28
    er
    0.27
    ro
    0.25
    after
    0.25
    t
    0.25
    le
    0.25
    on
    0.24
    l
    0.24
    us
    0.24
    POSITIVE LOGITS
     činjen
    0.26
    త్మిక
    0.25
     اسئله
    0.24
     الطريقه
    0.24
    ﺷ
    0.24
    ﷲ
    0.24
    ﻅ
    0.23
    ﺍ
    0.23
    commision
    0.23
    ALO
    0.23
    Activations Density 0.018%

    No Known Activations