INDEX

Explanations

words associated with objectives and time frames

oai_token-act-pair · gemini-2.0-flash

goals

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

 goals

-0.65

 goal

-0.61

 aims

-0.60

goal

-0.58

 Aims

-0.55

)];

-0.54

']));

-0.54

obiettivo

-0.54

aim

-0.53

goals

-0.53

POSITIVE LOGITS

SharedDtor

0.65

 Combien

0.57

AddTagHelper

0.54

 GoogleFonts

0.53

 xlink

0.53

 PARSER

0.53

ExecuteReader

0.52

PageRoute

0.51

 kaynağından

0.51

rrggbb

0.51

Activations Density 2.509%

words associated with objectives and time frames

goals

No Comments

No Known Activations