© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8598
    Prev
    Next
    INDEX
    Explanations

    text discussing vacations or missions involving other people, such as family members or students, with a focus on shared experiences.

    oai_token-act-pair · gemini-2.0-flash

    vacations and trips

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ujednoznacz
    -0.97
     Мексичка
    -0.95
     disambiguazione
    -0.95
    StoryboardSegue
    -0.92
    tvguidetime
    -0.92
     فريبيس
    -0.91
     كومونز
    -0.91
    MigrationBuilder
    -0.87
     resourceCulture
    -0.86
     للمعارف
    -0.86
    POSITIVE LOGITS
    R
    0.56
    se
    0.46
     R
    0.46
    WithType
    0.43
     sed
    0.43
    an
    0.40
    ses
    0.40
    va
    0.39
    sw
    0.38
    레
    0.38
    Activations Density 4.356%

    No Known Activations