© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130502
    Prev
    Next
    INDEX
    Explanations

    constant term

    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_25_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
     আগেও
    0.43
     மீன
    0.41
     Lui
    0.40
     தேவையான
    0.39
     periodontal
    0.38
     є
    0.38
    ancock
    0.38
     PAOK
    0.38
    peat
    0.38
     tangent
    0.38
    POSITIVE LOGITS
     sheds
    0.45
     نہيں
    0.42
     ofertas
    0.41
    ל
    0.40
     ucz
    0.39
    𒊬
    0.39
    شرين
    0.38
    𒅗
    0.38
    ד
    0.38
    bnb
    0.38
    Activations Density 0.000%

    No Known Activations