INDEX

Explanations

words related to the past, history, and politics

oai_token-act-pair · gemini-2.0-flash

history

np_token-act-pair-logits · gemini-2.0-flash

historical time periods

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 modern

-0.85

modern

-0.81

 moderne

-0.79

 centuries

-0.77

 archaic

-0.75

 moderno

-0.75

 moderni

-0.75

 historic

-0.74

historic

-0.73

 antiquated

-0.73

POSITIVE LOGITS

 Normdatei

0.66

#+#

0.65

 >=",

0.60

getJSONArray

0.57

 Région

0.54

日閲覧

0.54

 utafitiHapana

0.54

 propOrder

0.53

İstinadlar

0.52

mius

0.52

Activations Density 4.766%

words related to the past, history, and politics

history

historical time periods

No Comments

No Known Activations