INDEX

Explanations

words related to nuclear physics, atomic weapons, and defense

oai_token-act-pair · gemini-2.0-flash

nuclear

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

 ház

-0.56

 Exactos

-0.50

 nemlig

-0.50

 Signalez

-0.50

 beginnetje

-0.48

 trå

-0.47

 démocr

-0.46

 démocratique

-0.41

Rad

-0.41

 compagn

-0.41

POSITIVE LOGITS

ANTLR

0.79

FieldBuilder

0.71

日閲覧

0.63

Билгалдахарш

0.63

 Baillargeon

0.61

Kaynakça

0.61

ンダント

0.60

ASE

0.59

setVerticalGroup

0.59

ArgsConstructor

0.59

Activations Density 0.450%

words related to nuclear physics, atomic weapons, and defense

nuclear

No Comments

No Known Activations