INDEX

Explanations

words related to scientific or legal reasoning and data

oai_token-act-pair · gemini-2.0-flash

Technical/Scientific texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

awtextra

-0.67

 indications

-0.65

 evidence

-0.65

 Indications

-0.60

migrationBuilder

-0.59

QMetaType

-0.58

 indication

-0.55

 defaultstate

-0.54

="@+

-0.52

Indications

-0.52

POSITIVE LOGITS

vábbi

0.60

 originaux

0.57

FTFY

0.56

skap

0.53

ificados

0.53

نجليزية

0.52

horts

0.51

fant

0.50

 szóci

0.49

utsal

0.49

Activations Density 4.026%

words related to scientific or legal reasoning and data

Technical/Scientific texts

No Comments

No Known Activations