INDEX

Explanations

instances of something remaining unchanged

oai_token-act-pair · gemini-2.0-flash

remain

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 froide

-0.75

MLLoader

-0.72

ValueStyle

-0.69

 sorella

-0.69

 chaude

-0.68

 Maintaining

-0.63

 poire

-0.60

 resourceCulture

-0.60

rrggbb

-0.59

ंदीखरीदारी

-0.59

POSITIVE LOGITS

nóstico

0.56

unhofer

0.52

 Dafür

0.50

ophyllum

0.49

elcome

0.48

شكرا

0.47

raszamy

0.47

<?

0.47

0.46

 general

0.45

Activations Density 4.028%

instances of something remaining unchanged

remain

No Comments

No Known Activations