© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14618
    Prev
    Next
    INDEX
    Explanations

    very Common words and punctuation, as well as keywords 'help', 'know', and 'fixed'

    oai_token-act-pair · gemini-2.0-flash

    "u"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     вы
    -1.43
     Вы
    -1.13
     Sie
    -1.10
    Вы
    -1.07
     ВЫ
    -0.81
     you
    -0.77
     ви
    -0.72
    Sie
    -0.68
     jūs
    -0.67
     Ви
    -0.63
    POSITIVE LOGITS
     u
    2.63
     U
    1.85
    U
    1.77
    u
    1.71
     ur
    1.51
     uu
    1.04
    ｕ
    0.98
     Ur
    0.96
     uo
    0.94
     UR
    0.93
    Activations Density 6.681%

    No Known Activations