© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9612
    Prev
    Next
    INDEX
    Explanations

    the characters "Sa" in isolation or at the start of a word

    oai_token-act-pair · gemini-2.0-flash

    instances of the token "Sa"

    np_token-act-pair-logits · gpt-4o-mini

    Sa

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    rungsseite
    -0.84
    ChildScrollView
    -0.79
    Personendaten
    -0.73
    PhysRevD
    -0.72
    webElementXpaths
    -0.72
    CreateModel
    -0.71
     ModelExpression
    -0.71
    ResumeLayout
    -0.69
     kaarangay
    -0.69
    SourceChecksum
    -0.69
    POSITIVE LOGITS
    аб
    0.44
    ally
    0.44
    yttä
    0.44
    Ị
    0.41
    dist
    0.40
     tâ
    0.39
     Centers
    0.39
    ISTICS
    0.38
    Prove
    0.38
    WithMany
    0.37
    Activations Density 0.243%

    No Known Activations