© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5556
    Prev
    Next
    INDEX
    Explanations

    language about personal experiences and desires including the phrase "something to".

    oai_token-act-pair · gemini-2.0-flash

    adjectives describing positive qualities

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

    "something"

    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
    tagHelperRunner
    -0.90
    IUrlHelper
    -0.80
    MigrationBuilder
    -0.79
    LookAnd
    -0.75
    SourceChecksum
    -0.70
     Италијани
    -0.66
     ویکی‌پدی
    -0.65
    InjectAttribute
    -0.63
     defaultstate
    -0.62
     समीक्षाओं
    -0.62
    POSITIVE LOGITS
     new
    0.73
     recent
    0.68
     impressive
    0.68
     small
    0.68
     reputable
    0.66
     vibrant
    0.66
     strong
    0.65
     innovative
    0.65
     simple
    0.65
     beautiful
    0.65
    Activations Density 9.267%

    No Known Activations