INDEX

Explanations

instances of the word "can" or "could," sometimes accompanied by personal pronouns.

oai_token-act-pair · gemini-2.0-flash

can

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 roda

-0.47

twimg

-0.46

$_['

-0.43

 môn

-0.41

enda

-0.41

@"/

-0.41

USED

-0.41

moveToFirst

-0.41

Int

-0.41

исленность

-0.41

POSITIVE LOGITS

BagLayout

0.81

 JpaRepository

0.79

ngdoc

0.73

 odkazy

0.66

]")]

0.66

AndEndTag

0.65

tableFuture

0.61

 GUARANTEE

0.60

 guarantee

0.60

AddTagHelper

0.60

Activations Density 0.400%

instances of the word "can" or "could," sometimes accompanied by personal pronouns.

can

No Comments

No Known Activations