© 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. 214965
    Prev
    Next
    INDEX
    Explanations

    technical requirements, remediation

    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
     салу
    0.46
    嘞
    0.45
     सरस्व
    0.45
     কেশ
    0.42
     iremos
    0.42
     пап
    0.41
    <unused338>
    0.41
     रीठा
    0.40
    𝟕
    0.40
    etha
    0.39
    POSITIVE LOGITS
    Weather
    0.54
    Nuclear
    0.53
     vườn
    0.47
    Canadian
    0.46
    Self
    0.46
    Circuit
    0.46
     milit
    0.46
     nuclear
    0.46
     mémoire
    0.46
     ndi
    0.46
    Activations Density 0.000%

    No Known Activations