© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260598
    Prev
    Next
    INDEX
    Explanations

    over followed by quantity

    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
     longstanding
    0.22
     ቫ
    0.19
     ভয়ানক
    0.19
     anomalies
    0.19
     исключением
    0.18
     anomalous
    0.18
     pracovní
    0.18
    ্কর
    0.17
     hardness
    0.17
    ]));
    0.17
    POSITIVE LOGITS
    dit
    0.20
    di
    0.19
    irin
    0.19
    lais
    0.18
    wenden
    0.18
    лав
    0.18
    oru
    0.18
    abbit
    0.17
    ahit
    0.17
    idences
    0.17
    Activations Density 0.002%

    No Known Activations