© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14858
    Prev
    Next
    INDEX
    Explanations

    words ending in "ate" or "ies" or "ating"

    oai_token-act-pair · 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
    UnsafeEnabled
    -0.66
     estimés
    -0.65
    Попис
    -0.65
    RegressionTest
    -0.64
     estekak
    -0.61
    DockStyle
    -0.59
    FieldDescriptor
    -0.59
    intios
    -0.59
    PRWEB
    -0.58
     насеље
    -0.58
    POSITIVE LOGITS
    naires
    0.45
    +#+#
    0.41
    glGet
    0.39
    tep
    0.38
    ating
    0.38
    DropTable
    0.38
    abel
    0.36
    nestjs
    0.36
    tee
    0.35
    inWeight
    0.35
    Activations Density 6.308%

    No Known Activations