INDEX

Explanations

the word "kick" or "kick-off"

oai_token-act-pair · gemini-2.0-flash

kick

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

 CURIAM

-0.74

 estekak

-0.66

WillAppear

-0.66

 kaynağından

-0.65

RegressionTest

-0.61

دانشنامهٔ

-0.59

RunWith

-0.58

radioButton

-0.57

الإنجليزية

-0.57

parsedMessage

-0.56

POSITIVE LOGITS

tagHelperRunner

0.62

off

0.59

off

0.59

blatt

0.52

umptive

0.49

Off

0.47

 tartalomajánló

0.46

ksjoner

0.45

AndPassword

0.44

 offs

0.44

Activations Density 0.474%

the word "kick" or "kick-off"

kick

No Comments

No Known Activations