© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67770
    Prev
    Next
    INDEX
    Explanations

    say "ic" 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_51_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
     conspired
    0.38
    ངས་
    0.37
     appellees
    0.36
    }=$
    0.36
    ígono
    0.36
    怏
    0.36
    [$
    0.36
     handy
    0.36
    issel
    0.35
    $`
    0.35
    POSITIVE LOGITS
    мати
    0.58
    adic
    0.57
    matic
    0.57
    omatic
    0.55
    ytic
    0.54
    Matic
    0.52
    ographic
    0.50
    MATIC
    0.50
    uric
    0.49
    etic
    0.48
    Activations Density 0.011%

    No Known Activations