© 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. 12115
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "s/he" or related typos in text about research studies

    oai_token-act-pair · gemini-2.0-flash

    code and programming related

    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
     the
    -0.71
     un
    -0.53
     de
    -0.52
     so
    -0.51
     a
    -0.51
     free
    -0.50
     le
    -0.50
     first
    -0.48
     one
    -0.48
     more
    -0.47
    POSITIVE LOGITS
     avoient
    0.81
     étoient
    0.75
     cérami
    0.73
     jouets
    0.71
    httphttps
    0.71
     feroit
    0.70
     enfans
    0.69
    MigrationBuilder
    0.68
     traités
    0.67
     colorés
    0.66
    Activations Density 5.496%

    No Known Activations