© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258051
    Prev
    Next
    INDEX
    Explanations

    ways to cope

    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_22_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
    phon
    0.21
    Jogo
    0.20
     completes
    0.20
    translate
    0.19
    vana
    0.19
    con
    0.19
    쪽
    0.19
    izes
    0.19
    ਜ
    0.19
     adapté
    0.19
    POSITIVE LOGITS
     процессов
    0.22
     magnified
    0.20
     LDGs
    0.20
     सर्ट
    0.20
     المال
    0.20
     °,
    0.20
    丳
    0.20
    MutableArray
    0.20
     프로세
    0.20
     நினைவுச்சின்ன
    0.19
    Activations Density 0.003%

    No Known Activations