© 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. 7831
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to the television show "The Six Million Dollar Man"

    oai_token-act-pair · gemini-2.0-flash

    TV show reviews

    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
    <bos>
    -0.45
     دى
    -0.44
    idak
    -0.40
    EDEFAULT
    -0.40
    /$',
    -0.40
    imageio
    -0.40
     وتسجيلات
    -0.40
     ChromeDriver
    -0.40
     stdin
    -0.39
    UrlEncoded
    -0.39
    POSITIVE LOGITS
    BeginContext
    0.71
    AddTagHelper
    0.68
    ManagedBean
    0.66
     Loaf
    0.59
    :✨
    0.58
    localctx
    0.57
     &___
    0.57
     Bubbles
    0.56
     Vign
    0.56
     Balls
    0.56
    Activations Density 5.437%

    No Known Activations