INDEX

Explanations

tokens representing numbers and program modules

oai_token-act-pair · gemini-2.0-flash

Mixed foreign languages/code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.59

 Zufall

-0.45

 przesz

-0.44

QtGui

-0.44

lgica

-0.43

 AttributeSet

-0.43

ığ

-0.42

 ujednoznacz

-0.41

dinga

-0.41

 $("<

-0.41

POSITIVE LOGITS

 通販

0.66

 الرخصة

0.61

Manbalar

0.58

AddTagHelper

0.57

NewUrlParser

0.57

SequentialGroup

0.56

ésultat

0.56

$}}

0.56

WithEmail

0.56

LEncoder

0.55

Activations Density 0.143%

tokens representing numbers and program modules

Mixed foreign languages/code

No Comments

No Known Activations