INDEX

Explanations

words or characters often seen in business contexts, especially marketing

oai_token-act-pair · gemini-2.0-flash

Punctuation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 dieux

-0.72

 enfans

-0.65

 pauvres

-0.63

 supérieurs

-0.63

 Grecs

-0.63

 normaux

-0.61

 colorés

-0.61

 exemplaires

-0.60

 abandonné

-0.60

 élevées

-0.60

POSITIVE LOGITS

 Drapeau

0.46

 المعيارى

0.39

 Normdatei

0.39

 LUMP

0.38

Datuak

0.36

oblastoma

0.36

potranspiration

0.35

>>>>>>>>

0.35

béco

0.35

urances

0.34

Activations Density 8.973%

words or characters often seen in business contexts, especially marketing

Punctuation

No Comments

No Known Activations