INDEX

Explanations

instances of legal reasoning

oai_token-act-pair · gemini-2.0-flash

Summarizing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Above

-2.14

 above

-2.13

above

-2.08

 Above

-2.03

 ABOVE

-1.84

 mentioned

-1.73

below

-1.69

 below

-1.69

 acima

-1.59

mentioned

-1.58

POSITIVE LOGITS

 previously

1.05

 Previously

1.02

previously

0.96

 previous

0.94

Previously

0.94

 auparavant

0.87

 previamente

0.84

previous

0.81

 Previous

0.79

 PREVIOUS

0.79

Activations Density 1.744%

instances of legal reasoning

Summarizing

No Comments

No Known Activations