© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33868
    Prev
    Next
    INDEX
    Explanations

    negative prompt

    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_31_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
     আই
    0.21
    牯
    0.20
    lose
    0.20
    ONENT
    0.20
     Ion
    0.19
     grasses
    0.18
     explosion
    0.18
    সামরিক
    0.18
     explosions
    0.18
    憎
    0.18
    POSITIVE LOGITS
     Moulton
    0.21
     वर्कशीट
    0.19
    ల్లి
    0.19
    adType
    0.19
    ...'
    0.19
     सेमेस्टर
    0.19
    杠
    0.19
    oselect
    0.18
     smtp
    0.18
    ...(
    0.18
    Activations Density 0.000%

    No Known Activations