© 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. 17370
    Prev
    Next
    INDEX
    Explanations

    narrative and story

    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
     zape
    0.39
    拁
    0.38
    Copies
    0.37
     رک
    0.36
     sensitized
    0.36
     Samp
    0.35
    Wrist
    0.34
     deposits
    0.34
    REAT
    0.34
    搔
    0.34
    POSITIVE LOGITS
     narrative
    1.13
    ストーリー
    1.09
     storyline
    1.08
     storytelling
    1.05
     Narrative
    0.98
     storylines
    0.96
     narrativa
    0.95
     narratives
    0.95
     story
    0.94
    story
    0.91
    Activations Density 0.235%

    No Known Activations