INDEX

Explanations

words and section titles related to scientific research papers, especially those about health interventions with children or conscripts

oai_token-act-pair · gemini-2.0-flash

ijer

np_max-act · gemini-2.0-flash

New Auto-Interp

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

 beginnetje

-0.88

runOnUiThread

-0.85

__':

-0.78

<bos>

-0.75

 chi̍t

-0.73

enderror

-0.70

 betweenstory

-0.70

conazole

-0.70

popularity

-0.68

Enllaços

-0.67

POSITIVE LOGITS

0.56

 Secured

0.52

Hochspringen

0.52

 Juga

0.49

cshtml

0.47

<<

0.46

 perus

0.46

 controll

0.45

 copi

0.45

 spéciales

0.45

Activations Density 7.779%

words and section titles related to scientific research papers, especially those about health interventions with children or conscripts

ijer

No Comments

No Known Activations