© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237037
    Prev
    Next
    INDEX
    Explanations

    intent or certainty

    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_46_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
     scor
    0.43
    recall
    0.43
    응
    0.41
    നേ
    0.41
     remember
    0.41
    钎
    0.41
    からです
    0.38
    Scorch
    0.38
    ามารถ
    0.38
    झ
    0.38
    POSITIVE LOGITS
     deliberately
    0.51
    Obviously
    0.48
     Obviously
    0.48
     purposely
    0.46
     креди
    0.45
     Definitely
    0.44
     intentionally
    0.43
     evidentemente
    0.43
     deliberate
    0.43
     knowingly
    0.42
    Activations Density 0.016%

    No Known Activations