© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11061
    Prev
    Next
    INDEX
    Explanations

    strings 'aj', 'dej', and 'maj' in online forum usernames

    oai_token-act-pair · gemini-2.0-flash

    oj

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AutoScaleMode
    -0.83
    AnchorStyles
    -0.80
     ivelany
    -0.77
    TagMode
    -0.76
    SequentialGroup
    -0.75
     ujednoznacz
    -0.69
    ]")]
    -0.69
    Personendaten
    -0.67
     HasFactory
    -0.67
     betweenstory
    -0.64
    POSITIVE LOGITS
     AssemblyProduct
    0.53
    Geno
    0.46
     CharSequence
    0.44
     RegExp
    0.42
    şme
    0.42
     weakness
    0.42
    Spare
    0.42
    uclear
    0.42
    [++
    0.41
     Greece
    0.40
    Activations Density 0.530%

    No Known Activations