© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1706
    Prev
    Next
    INDEX
    Explanations

    uses of the subject "I" or "me" in German, and religious terms in English.

    oai_token-act-pair · gemini-2.0-flash

    say "pr/r/str/vi/v"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    principalColumn
    -1.24
    Personendaten
    -1.20
    ConstraintMaker
    -1.19
     nakalista
    -1.11
     betweenstory
    -1.11
    تقاوى
    -1.06
    RetentionPolicy
    -1.04
    Personensuche
    -1.02
    BeginContext
    -0.98
     kasarigan
    -0.97
    POSITIVE LOGITS
    pr
    0.44
    r
    0.43
    str
    0.43
    宿
    0.43
    vi
    0.42
    v
    0.42
    Range
    0.42
    range
    0.41
     υπο
    0.41
     range
    0.41
    Activations Density 0.871%

    No Known Activations