© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100036
    Prev
    Next
    INDEX
    Explanations

    sent a message or email

    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_14_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
    hui
    0.49
    あるいは
    0.43
    aménagement
    0.41
    ipkan
    0.41
    ampunk
    0.41
    /?
    0.40
    linic
    0.40
     וח
    0.39
     ${\
    0.39
     मनोर
    0.39
    POSITIVE LOGITS
     rufo
    0.49
     fatta
    0.48
    노
    0.47
     rutas
    0.47
     roja
    0.47
     penalties
    0.46
     sheaves
    0.46
    카
    0.45
     actualizada
    0.44
    𝘿
    0.44
    Activations Density 0.039%

    No Known Activations