© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 261385
    Prev
    Next
    INDEX
    Explanations

    timestamps and dates

    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_5_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
    т
    1.32
     supremely
    1.23
    ación
    1.20
     conflicting
    1.16
    larının
    1.11
    р
    1.11
     booted
    1.10
    ро
    1.09
    ución
    1.09
    이다
    1.09
    POSITIVE LOGITS
    2
    1.96
    7
    1.50
    8
    1.47
    ai
    1.46
    1
    1.41
    c
    1.38
    im
    1.37
    6
    1.34
    ah
    1.32
    Data
    1.30
    Activations Density 0.000%

    No Known Activations