INDEX

Explanations

code-related keywords such as null, false and parenthesis

oai_token-act-pair · gemini-2.0-flash

null

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

__*/

-0.57

rieks

-0.48

taker

-0.45

hlander

-0.45

ioutil

-0.45

prehen

-0.44

 Serie

-0.44

 cận

-0.43

 ejes

-0.43

newArrayList

-0.43

POSITIVE LOGITS

AddTagHelper

0.75

 насељу

0.65

ConstraintMaker

0.60

 HasFactory

0.60

PreferredItem

0.59

ValueStyle

0.58

جمعیت

0.58

phrag

0.57

IUrlHelper

0.57

ukone

0.56

Activations Density 1.470%

code-related keywords such as null, false and parenthesis

null

No Comments

No Known Activations