INDEX

Explanations

words related to disagreements and reasoning with others, including politics and religion

oai_token-act-pair · gemini-2.0-flash

disagreement

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

GEBURTSDATUM

-0.83

 ProtoMessage

-0.74

 Monfieur

-0.64

setVerticalGroup

-0.59

kozó

-0.59

verwijspagina

-0.57

Personensuche

-0.56

 архивлан

-0.53

protoimpl

-0.53

bigoplus

-0.52

POSITIVE LOGITS

ruptedException

0.51

AndroidJUnit

0.48

 INTERESAR

0.46

病

0.46

 GetEnumerator

0.46

RTRS

0.45

 discretion

0.43

eronau

0.43

 metal

0.42

andri

0.42

Activations Density 59.682%

words related to disagreements and reasoning with others, including politics and religion

disagreement

No Comments

No Known Activations