© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35244
    Prev
    Next
    INDEX
    Explanations

    по воздушной тревоге

    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_31_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
    flatten
    0.39
    handlebars
    0.39
     explores
    0.38
     grows
    0.38
    ỡ
    0.38
    timezone
    0.37
     iguais
    0.37
     handlebar
    0.36
    handle
    0.36
     handlebars
    0.36
    POSITIVE LOGITS
    баев
    0.39
    俆
    0.38
    <0x16>
    0.37
     나타
    0.37
     ఆధ్యాత్మిక
    0.37
    embre
    0.36
     privada
    0.36
    無料で
    0.36
    若干
    0.35
    ">)</
    0.35
    Activations Density 0.001%

    No Known Activations