INDEX

Explanations

military ranks, units, and related terms (e.g., awards).

oai_token-act-pair · gemini-2.0-flash

military

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

tagHelperRunner

-0.80

rungsseite

-0.73

MigrationBuilder

-0.58

IsContent

-0.56

webElementXpaths

-0.55

Autoritní

-0.53

kegaard

-0.47

AndEndTag

-0.47

DeleteBehavior

-0.46

 Scrooge

-0.46

POSITIVE LOGITS

 military

1.33

Military

1.21

 Military

1.21

military

1.19

 militare

1.16

 army

1.14

 Army

1.13

 MILITARY

1.10

 militaires

1.09

 militar

1.08

Activations Density 2.226%

military ranks, units, and related terms (e.g., awards).

military

No Comments

No Known Activations