© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12117
    Prev
    Next
    INDEX
    Explanations

    the word "them" along with personal pronouns or words indicating spatial location

    oai_token-act-pair · gemini-2.0-flash

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     “
    -0.50
    bled
    -0.48
    cipline
    -0.48
    INFORM
    -0.46
    makeText
    -0.44
    bex
    -0.43
    YY
    -0.42
    ngilizce
    -0.42
    yml
    -0.42
     ممن
    -0.41
    POSITIVE LOGITS
    GOTREF
    0.90
    SBATCH
    0.80
     للاسماء
    0.79
     متعلقه
    0.77
    ngdoc
    0.76
    andExpect
    0.73
    NewGuid
    0.73
     userSchema
    0.69
    AndEndTag
    0.69
    LLocation
    0.67
    Activations Density 1.030%

    No Known Activations