© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118935
    Prev
    Next
    INDEX
    Explanations

    POST, char, API, xhr

    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_27_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
     camer
    0.37
     всі
    0.36
     nam
    0.35
    organiz
    0.35
    href
    0.35
    浾
    0.34
     amplified
    0.34
     MEDIC
    0.34
     scuole
    0.34
     nitrate
    0.33
    POSITIVE LOGITS
    턱
    0.41
    Answer
    0.41
    Synth
    0.39
    噜
    0.39
     (£
    0.39
     शीर्षक
    0.38
    Situated
    0.37
     Situated
    0.37
     संवेदनशील
    0.36
     answer
    0.36
    Activations Density 0.000%

    No Known Activations