© 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. 957
    Prev
    Next
    INDEX
    Explanations

    code or code-like text

    oai_token-act-pair · gemini-2.0-flash

    "<"

    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
    دانشنامهٔ
    -0.71
     صوتيه
    -0.68
     الحره
    -0.68
     الاطلاع
    -0.66
    pement
    -0.66
     незавершена
    -0.66
    bliž
    -0.65
     autorytatywna
    -0.65
    :✨
    -0.65
     سكانية
    -0.64
    POSITIVE LOGITS
    ProductService
    0.63
     And
    0.60
    UserService
    0.59
    LogFactory
    0.57
    UserDto
    0.57
    MatIconModule
    0.56
    LoginActivity
    0.55
     But
    0.54
    UserDao
    0.53
    OrderService
    0.51
    Activations Density 5.206%

    No Known Activations