© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7064
    Prev
    Next
    INDEX
    Explanations

    small, common words used in formal writing

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ษ
    -0.49
     
    -0.41
    tikan
    -0.41
     Borg
    -0.41
     Im
    -0.41
    Override
    -0.40
    клопе
    -0.39
    Hoy
    -0.39
    override
    -0.39
    cored
    -0.38
    POSITIVE LOGITS
     this
    2.05
    this
    1.55
     questo
    1.28
     questa
    1.25
     này
    1.25
     denna
    1.21
    This
    1.20
     этой
    1.16
     diesem
    1.16
     этого
    1.15
    Activations Density 2.026%

    No Known Activations