© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15034
    Prev
    Next
    INDEX
    Explanations

    legal jargon and references (testimony, claims, defendant, evidence).

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    AndEndTag
    -0.85
    httphttps
    -0.79
     betweenstory
    -0.76
    Personendaten
    -0.71
    DockStyle
    -0.71
     disambiguazione
    -0.70
    styleType
    -0.70
     MatDialog
    -0.69
    saraba
    -0.68
    WebVitals
    -0.68
    POSITIVE LOGITS
    że
    0.52
     diing
    0.47
     Originally
    0.46
    arakhand
    0.44
     appunt
    0.44
    diğini
    0.43
    vasti
    0.43
     Púb
    0.43
     víctima
    0.42
     who
    0.41
    Activations Density 26.727%

    No Known Activations