INDEX

Explanations

the string "pr" followed by other characters

oai_token-act-pair · gemini-2.0-flash

scientific research

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

 fellowship

-0.82

 fellowships

-0.73

 fellows

-0.71

 grant

-0.64

oredCriteria

-0.61

 Visiting

-0.60

 Fellowship

-0.59

fellow

-0.58

:✨

-0.58

grant

-0.57

POSITIVE LOGITS

 curé

0.51

 consultato

0.51

 LUMP

0.48

PerformLayout

0.47

 vedette

0.46

 encima

0.45

Véxase

0.45

 onCreateView

0.44

RegressionTest

0.44

 onView

0.43

Activations Density 0.537%

the string "pr" followed by other characters

scientific research

No Comments

No Known Activations