© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167993
    Prev
    Next
    INDEX
    Explanations

    additional details or costs

    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_34_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
     నిర్వహ
    0.49
     индиви
    0.43
    Rajas
    0.42
     Kontak
    0.41
    ліза
    0.40
    㑬
    0.40
     Boulder
    0.40
    ริญ
    0.39
     Veranst
    0.39
    開催
    0.39
    POSITIVE LOGITS
     untenable
    0.36
    シュ
    0.35
    ථා
    0.35
     영화
    0.35
    speak
    0.35
     가수
    0.33
    봉
    0.33
    놓
    0.33
     screenwriter
    0.33
    antiate
    0.32
    Activations Density 0.001%

    No Known Activations