© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160430
    Prev
    Next
    INDEX
    Explanations

    Be followed by adjectives or nouns

    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
    та
    1.51
     ότι
    1.46
    that
    1.30
     что
    1.24
    ا
    1.21
     لأ
    1.20
    وأ
    1.19
     парт
    1.17
     цве
    1.13
    প্রায়
    1.10
    POSITIVE LOGITS
    n
    1.45
    c
    1.45
    s
    1.30
    k
    1.30
    g
    1.27
    t
    1.18
    st
    1.16
     I
    1.15
     It
    1.13
    S
    1.11
    Activations Density 0.010%

    No Known Activations