© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13015
    Prev
    Next
    INDEX
    Explanations

    terms referencing social media like Facebook, Instagram and news, and legal terms like murder and kill

    oai_token-act-pair · gemini-2.0-flash

    social media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     vägen
    -0.58
     Dernière
    -0.57
    RegressionTest
    -0.56
    DoubleQuotes
    -0.56
     Haig
    -0.54
     veau
    -0.54
     consultato
    -0.54
     voies
    -0.53
    trainable
    -0.52
    HasOne
    -0.52
    POSITIVE LOGITS
    ſelf
    0.54
    ">:
    0.54
     Jefus
    0.51
     myſelf
    0.51
    HideInInspector
    0.49
    \}\\
    0.49
    তথ্যসূত্র
    0.47
    };*/
    0.47
    ‍♀️
    0.47
    JEE
    0.47
    Activations Density 9.630%

    No Known Activations