© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79199
    Prev
    Next
    INDEX
    Explanations

    horrific, Russkaya Pravda

    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_0_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
    ή
    1.45
    ની
    1.32
    ด์
    1.27
    지
    1.26
    는
    1.24
    ת
    1.22
    కు
    1.20
    正
    1.20
    ع
    1.19
    ق
    1.19
    POSITIVE LOGITS
    ER
    1.51
    u
    1.47
    ITATION
    1.30
    3
    1.26
    iden
    1.20
    owali
    1.18
    le
    1.17
    IT
    1.16
    IV
    1.15
    IS
    1.13
    Activations Density 0.000%

    No Known Activations