© 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-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3548
    Prev
    Next
    INDEX
    Explanations

    following numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    el
    0.24
    id
    0.23
    ik
    0.20
    ico
    0.20
    verso
    0.20
    ق
    0.20
    et
    0.20
    츄
    0.19
    dbo
    0.19
    w
    0.19
    POSITIVE LOGITS
     infamous
    0.29
    +}(
    0.26
    +}^{
    0.25
     misdeme
    0.25
     \]
    0.25
    leqslant
    0.24
    десь
    0.24
    ({\
    0.24
     국내
    0.24
    """)
    0.24
    Activations Density 0.109%

    No Known Activations