© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132157
    Prev
    Next
    INDEX
    Explanations

    i followed by punctuation or specific words

    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_1_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
    ہ
    1.41
    c
    1.18
    }$.
    1.15
    ку
    1.12
    을
    1.09
    ਨ
    1.09
    к
    1.09
    生
    1.05
    手
    1.04
     to
    1.02
    POSITIVE LOGITS
    い
    1.31
    '
    1.27
    :
    1.09
    at
    1.05
    ва
    1.02
    <0x80>
    1.00
    ent
    1.00
    inė
    0.99
    D
    0.96
    י
    0.96
    Activations Density 0.000%

    No Known Activations