© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10123
    Prev
    Next
    INDEX
    Explanations

    words related to future expectation or possibility

    oai_token-act-pair · gemini-2.0-flash

    anticipation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     cannot
    -1.14
     Cannot
    -1.04
    cannot
    -1.04
     cant
    -1.02
    Cannot
    -0.98
    cant
    -0.92
     CANT
    -0.91
     CANNOT
    -0.85
    Cant
    -0.85
     inability
    -0.81
    POSITIVE LOGITS
    ();)
    0.60
    ślę
    0.53
    tinyos
    0.52
     yourself
    0.52
     FontWeight
    0.52
    jenigen
    0.52
     additionally
    0.51
    baomidou
    0.51
     notare
    0.50
    ftagPool
    0.50
    Activations Density 2.212%

    No Known Activations