© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10623
    Prev
    Next
    INDEX
    Explanations

    words that indicate moving away from something, whether physically or ideologically.

    oai_token-act-pair · gemini-2.0-flash

    away

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyVersion
    -0.89
     beginnetje
    -0.68
     OMIT
    -0.67
    GrantedAuthority
    -0.66
    قایناق‌لار
    -0.65
     חיצוניים
    -0.64
    +#+#
    -0.64
     AppComponent
    -0.64
    ControllerAdvice
    -0.64
     JAXBElement
    -0.63
    POSITIVE LOGITS
     up
    0.60
    up
    0.55
     from
    0.50
     –
    0.48
     مواليد
    0.45
    ắn
    0.44
    rrggbb
    0.41
    Up
    0.39
    venant
    0.39
    form
    0.39
    Activations Density 10.250%

    No Known Activations