© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 198016
    Prev
    Next
    INDEX
    Explanations

    say "ador" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Dise
    0.42
    methylene
    0.41
    壹章
    0.41
     Fatigue
    0.40
     methylene
    0.38
     garnis
    0.38
     fatigue
    0.37
    ::$
    0.37
    wallepics
    0.37
    ulty
    0.36
    POSITIVE LOGITS
    ador
    1.60
    ADOR
    1.48
    adores
    1.41
    adors
    1.41
     dor
    1.30
    idor
    1.26
    adoras
    1.25
    dor
    1.23
    adore
    1.23
    adora
    1.22
    Activations Density 0.004%

    No Known Activations