© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15992
    Prev
    Next
    INDEX
    Explanations

    ABAP report names

    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
     neck
    0.36
     astăzi
    0.35
     chargés
    0.34
     Hedgehog
    0.33
    Ladies
    0.33
    と
    0.33
     cuello
    0.33
    Slot
    0.33
    Pag
    0.33
     ladies
    0.33
    POSITIVE LOGITS
    ിക്കാൻ
    0.39
    🙎
    0.39
    思う
    0.36
     Affidavit
    0.35
    十壹章
    0.34
    簡易
    0.34
     よる
    0.34
    arranty
    0.33
    वेदनशील
    0.33
     REGIUNI
    0.33
    Activations Density 0.001%

    No Known Activations