© 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. 4125
    Prev
    Next
    INDEX
    Explanations

    German text that includes parentheses and discusses writing letters and sentences, particularly focusing on the use of verbs

    oai_token-act-pair · gemini-2.0-flash

    Ich

    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
     will
    -0.82
     kasarigan
    -0.81
    will
    -0.62
     الحره
    -0.60
    oplasma
    -0.60
    ishw
    -0.60
     Baillargeon
    -0.58
    DockStyle
    -0.58
    iibo
    -0.57
    PYX
    -0.56
    POSITIVE LOGITS
    artifactId
    0.50
    MigrationBuilder
    0.49
    elemField
    0.48
    bited
    0.45
    ранда
    0.44
    localctx
    0.44
     řekl
    0.43
     kulak
    0.43
    marginRight
    0.42
    jface
    0.42
    Activations Density 0.364%

    No Known Activations