INDEX

Explanations

phrases that introduce mathematical theorems and results

oai_token-act-pair · gemini-2.0-flash

need

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

CWE

-0.53

NewRow

-0.48

 infinitesimal

-0.47

ोंने

-0.46

 MyBatis

-0.45

dymyr

-0.45

GetBytes

-0.44

テイン

-0.43

сылкі

-0.43

crans

-0.43

POSITIVE LOGITS

 needed

1.77

needed

1.60

 need

1.56

 Needed

1.52

 needs

1.47

need

1.45

 Need

1.42

 NEEDED

1.42

 needing

1.38

 Needs

1.36

Activations Density 1.685%

phrases that introduce mathematical theorems and results

need

No Comments

No Known Activations