INDEX

Explanations

code-related language along with the word default

oai_token-act-pair · gemini-2.0-flash

default

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InStock

-0.47

Ayu

-0.44

 puteți

-0.43

 peacock

-0.41

 zápas

-0.40

 volcan

-0.39

sortable

-0.39

 Vist

-0.39

 ellers

-0.39

DataSetChanged

-0.39

POSITIVE LOGITS

Datuak

0.76

 beginnetje

0.74

 Paglinawan

0.71

Geplaatst

0.71

__":

0.69

 كومونز

0.68

NOPQRST

0.68

WebElementEntity

0.67

ClCompile

0.66

 समीक्षाओं

0.66

Activations Density 1.615%

code-related language along with the word default

default

No Comments

No Known Activations