© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16280
    Prev
    Next
    INDEX
    Explanations

    movie titles, film-related words, and colons

    oai_token-act-pair · gemini-2.0-flash

    movie titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CreateTagHelper
    -0.57
    তথ্যসূত্র
    -0.47
    ="@+
    -0.47
    kegaard
    -0.46
     trang
    -0.46
     secondaires
    -0.45
     bords
    -0.45
    ünf
    -0.44
     doInBackground
    -0.44
    posedge
    -0.44
    POSITIVE LOGITS
    UnknownFieldSet
    0.62
     chariot
    0.54
    InteropServices
    0.53
     Apu
    0.52
     unison
    0.52
    ברס
    0.50
    ầng
    0.50
    )))));
    0.50
    XXV
    0.50
     fanfare
    0.49
    Activations Density 1.509%

    No Known Activations