© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260883
    Prev
    Next
    INDEX
    Explanations

    frequently followed by verbs or prepositions

    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_5_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
    r
    1.85
    m
    1.82
    f
    1.69
    st
    1.67
    b
    1.55
    j
    1.53
    w
    1.48
    ad
    1.48
    h
    1.43
    un
    1.41
    POSITIVE LOGITS
    ↵
    1.13
    </h3>
    1.00
    -
    0.93
    あまり
    0.91
    지를
    0.86
    лько
    0.86
    什么
    0.86
    য়া
    0.86
    ן
    0.86
    </h6>
    0.84
    Activations Density 0.000%

    No Known Activations