© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100678
    Prev
    Next
    INDEX
    Explanations

    stalker Zone

    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_16_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
    kyverno
    0.60
    膾
    0.58
    జ్ఞ
    0.56
    OrderFlight
    0.54
    lge
    0.54
     સમય
    0.53
     आत्मविश्वास
    0.53
     مليار
    0.52
    භාව
    0.52
     নির্ভরযোগ্য
    0.52
    POSITIVE LOGITS
    ="
    0.54
    <strong>
    0.52
    </div>
    0.52
    ara
    0.52
     \\
    0.48
     &&
    0.48
    Þ
    0.47
    をつけて
    0.47
    </
    0.46
     decides
    0.46
    Activations Density 0.001%

    No Known Activations