INDEX

Explanations

quantifiers, especially when they are associated with social issues

oai_token-act-pair · gemini-2.0-flash

small quantity

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

:✨

-0.79

fjspx

-0.75

Билгалдахарш

-0.73

httphttps

-0.72

 ivelany

-0.71

]")]

-0.69

 nakalista

-0.69

expandindo

-0.69

 FormGroup

-0.69

Enllaces

-0.69

POSITIVE LOGITS

 minority

1.22

few

0.90

 Minority

0.83

 small

0.82

 fraction

0.79

few

0.74

 percentage

0.72

 MINOR

0.71

少

0.71

 minorities

0.69

Activations Density 1.510%

quantifiers, especially when they are associated with social issues

small quantity

No Comments

No Known Activations