© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37915
    Prev
    Next
    INDEX
    Explanations

    say "ine" ending

    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_57_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
    イン
    0.52
    인
    0.50
    Ин
    0.48
     ин
    0.48
    인을
    0.46
     인
    0.45
    인은
    0.44
    인이
    0.44
    인의
    0.41
    إن
    0.41
    POSITIVE LOGITS
    INE
    1.81
    ine
    1.79
    ines
    1.64
     ine
    1.63
     INE
    1.58
    Ine
    1.55
     ne
    1.50
    INES
    1.44
     sine
    1.34
     tine
    1.30
    Activations Density 0.053%

    No Known Activations