© 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
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261193
    Prev
    Next
    INDEX
    Explanations

    TFT or jig

    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
    ،
    1.59
    ，
    1.32
    、
    1.19
    ren
    1.16
    ၊
    1.15
    та
    1.05
    ين
    1.05
    ny
    1.03
    nek
    1.00
    ning
    0.98
    POSITIVE LOGITS
    "
    1.37
    SE
    1.33
    CH
    1.30
    AD
    1.27
    হ
    1.26
    ר
    1.22
     as
    1.16
    お店
    1.13
    IM
    1.13
    MS
    1.09
    Activations Density 0.000%

    No Known Activations